{ "complete": true, "report": { "bucket": "emo_Triumph", "label": "Intense Triumph", "definition": { "id": "emo_Triumph", "category": "emotion", "head": "emo_Triumph", "pole": "high", "label": "Intense Triumph", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_triumph/full-v2-sealed/sealed-selected", "mission": "emotion_triumph", "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": 6.255095653533935, "genuineness": 4.056037058830261, "wer": 0.012598711969123537, "identity": 0.6016334541141987, "voiceclap": 0.011052084974944592, "fitness": 0.6415924968548677, "steering_v2": 0.6484584978798261, "raw_target": 0.5387977959960699, "target_cdf": 0.6484584978798261, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.266453685760498, "genuineness": 4.025221691131592, "wer": 0.016200843780376596, "identity": 0.6016334541141987, "fitness": 0.6366525746475943, "steering_v2": 0.6457108412226491 }, "none": { "n": 50, "ce": 6.243737621307373, "genuineness": 4.086852426528931, "wer": 0.008996580157870481, "identity": null, "fitness": 0.6465324190621411, "steering_v2": 0.6512061545370033 } } } } ], "selected_wording": { "id": "manual-f9f56f50b9e3", "general": "Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.", "inline": [ "Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.", "Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.", "Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge." ], "cfg": 3, "recipe": "P06", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 2.213110394133818, "target_raw": 1.3616676762700082, "ce": 5.988857245445251, "genuineness": 4.0743003487586975, "identity": 0.5096721395850181, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.0664634183049202, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 0.6361328250010357, "target_raw": 0.5289980515837669, "ce": 6.176304292678833, "genuineness": 4.282351088523865, "identity": 0.5653797134757041, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.010755844414234161, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 2.213110394133818, "target_raw": 1.3616676762700082, "ce": 5.988857245445251, "genuineness": 4.0743003487586975, "identity": 0.5096721395850181, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.0664634183049202, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 2.17294920434184, "target_raw": 1.3404619194567204, "ce": 5.8595902681350704, "genuineness": 4.0005568861961365, "identity": 0.40372461527585984, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.17241094261407852, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 2.149951219944459, "target_raw": 1.3283186122775077, "ce": 5.7821491956710815, "genuineness": 3.982356333732605, "identity": 0.4438695304095745, "wer": 0.02673611111111111, "valid_fraction": 0.9, "identity_delta": -0.13226602748036384, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 1.7306640727962674, "target_raw": 1.106928227096796, "ce": 6.075829482078552, "genuineness": 4.0761831402778625, "identity": 0.45122132673859594, "wer": 0.01067251461988304, "valid_fraction": 1, "identity_delta": -0.1249142311513424, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 1.2244384818732355, "target_raw": 0.8396329395473003, "ce": 6.12666265964508, "genuineness": 4.217394089698791, "identity": 0.4944385468959808, "wer": 0.014298245614035088, "valid_fraction": 0.95, "identity_delta": -0.08169701099395751, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 0.7782348909386891, "target_raw": 0.6040302373468875, "ce": 6.164588880538941, "genuineness": 4.243753445148468, "identity": 0.5235808044672012, "wer": 0.024853801169590642, "valid_fraction": 0.95, "identity_delta": -0.05255475342273712, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 0.707629420810709, "target_raw": 0.5667494088411331, "ce": 6.17253155708313, "genuineness": 4.23057370185852, "identity": 0.5221814148128032, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": -0.053954143077135086, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 0.48184204411263537, "target_raw": 0.44753002747893333, "ce": 6.203309440612793, "genuineness": 4.319065880775452, "identity": 0.5124239094555378, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.06371164843440055, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 0.6361328250010357, "target_raw": 0.5289980515837669, "ce": 6.176304292678833, "genuineness": 4.282351088523865, "identity": 0.5653797134757041, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.010755844414234161, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 0.5254394579258828, "target_raw": 0.4705501660704613, "ce": 6.182261347770691, "genuineness": 4.318124508857727, "identity": 0.5342200174927711, "wer": 0.007894736842105263, "valid_fraction": 0.95, "identity_delta": -0.0419155403971672, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 0.40439453410517484, "target_raw": 0.4066364914178848, "ce": 6.126861190795898, "genuineness": 4.2807820558547975, "identity": 0.5500382732599973, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.026097284629940987, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 2.822851654108119, "target_raw": 1.6836209088563918, "ce": 5.747598671913147, "genuineness": 3.92822550535202, "identity": 0.41271193958818914, "wer": 0.011312134502923977, "valid_fraction": 1, "identity_delta": -0.16342361830174923, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 2.6602539768797495, "target_raw": 1.5977667093276977, "ce": 5.685645794868469, "genuineness": 3.982983946800232, "identity": 0.4072555683553219, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": -0.16887998953461647, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 2.477124063104036, "target_raw": 1.5010711573064328, "ce": 5.902480697631836, "genuineness": 3.955683195590973, "identity": 0.4554731948301196, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": -0.12066236305981874, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 2.472607461742721, "target_raw": 1.4986863188445567, "ce": 5.818884110450744, "genuineness": 3.9734129786491392, "identity": 0.4543648768216372, "wer": 0.011968954248366012, "valid_fraction": 1, "identity_delta": -0.1217706810683012, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 2.4345215592323926, "target_raw": 1.478576347231865, "ce": 5.706892442703247, "genuineness": 4.009029519557953, "identity": 0.42180417478084564, "wer": 0.01727704678362573, "valid_fraction": 1, "identity_delta": -0.15433138310909272, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 2.386621158933972, "target_raw": 1.4532841622829438, "ce": 5.828315949440002, "genuineness": 3.9578797936439516, "identity": 0.41691366024315357, "wer": 0.00804093567251462, "valid_fraction": 1, "identity_delta": -0.1592218976467848, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 2.1657959302109657, "target_raw": 1.336684875190258, "ce": 5.995608472824097, "genuineness": 4.036016464233398, "identity": 0.46976084522902967, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.1063747126609087, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 2.0152344191394596, "target_raw": 1.2571859657764435, "ce": 6.015068078041077, "genuineness": 4.070220935344696, "identity": 0.4518140607513487, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.12432149713858962, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 1.930761750024637, "target_raw": 1.2125830322504043, "ce": 6.059547042846679, "genuineness": 4.09971832036972, "identity": 0.41130341552197935, "wer": 0.016666666666666666, "valid_fraction": 0.95, "identity_delta": -0.164832142367959, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.6537842373339207, "target_raw": 1.0663344323635102, "ce": 6.062525534629822, "genuineness": 4.096894085407257, "identity": 0.4938552647829056, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.08228029310703278, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 1.6484375149924237, "target_raw": 1.0635112766176462, "ce": 6.113755750656128, "genuineness": 4.133608973026275, "identity": 0.5185558542609214, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.057579703629016876, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.3793213146350551, "target_raw": 0.9214135766029358, "ce": 6.071858143806457, "genuineness": 4.13329508304596, "identity": 0.4919346529990435, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.08420090489089489, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 1.2363281512367417, "target_raw": 0.8459108769893646, "ce": 6.161808943748474, "genuineness": 4.169382357597351, "identity": 0.5159118279814721, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.06022372990846634, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 1.0367675816471171, "target_raw": 0.7405396733433008, "ce": 6.118322825431823, "genuineness": 4.210176622867584, "identity": 0.49517902042716744, "wer": 0.005902777777777778, "valid_fraction": 1, "identity_delta": -0.08095653746277094, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 1.01713867285061, "target_raw": 0.7301752924919128, "ce": 6.165581679344177, "genuineness": 4.223042476177215, "identity": 0.5052637726068496, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.07087178528308868, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 0.8713623095517699, "target_raw": 0.6532030183821916, "ce": 6.181069946289062, "genuineness": 4.320948672294617, "identity": 0.4871387429535389, "wer": 0.010964912280701754, "valid_fraction": 1, "identity_delta": -0.08899681493639947, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 0.7783935933288187, "target_raw": 0.6041140347719193, "ce": 6.190998268127442, "genuineness": 4.227749538421631, "identity": 0.5011222966015338, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.07501326128840446, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 0.7298828419336555, "target_raw": 0.578499574586749, "ce": 6.197749543190002, "genuineness": 4.345425295829773, "identity": 0.5071052104234696, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.06903034746646881, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 0.6866943318393871, "target_raw": 0.5556953437626362, "ce": 6.222768974304199, "genuineness": 4.278271627426148, "identity": 0.46709272265434265, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.1090428352355957, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 0.5360351541223987, "target_raw": 0.476144864782691, "ce": 6.1880197763443, "genuineness": 4.277016389369964, "identity": 0.5148873046040535, "wer": 0.008333333333333333, "valid_fraction": 1, "identity_delta": -0.06124825328588486, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 0.45916746852028434, "target_raw": 0.4355574853718281, "ce": 6.2068836212158205, "genuineness": 4.351387524604798, "identity": 0.5230883941054344, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.053047163784503935, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": 0.09714965591223304, "target_raw": 0.24440623372793197, "ce": 6.225151753425598, "genuineness": 4.291765093803406, "identity": 0.5761355578899383, "wer": 0.005263157894736842, "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": 0.03255003716145625, "target_raw": 0.21029659174382687, "ce": 6.18464412689209, "genuineness": 4.320948803424836, "identity": 0.5550056554377079, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.021129902452230453, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": 0.04515990940371102, "target_raw": 0.21695480793714522, "ce": 6.236271524429322, "genuineness": 4.302748143672943, "identity": 0.5750516876578331, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.0010838702321052552, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.006103523666892025, "target_raw": 0.18988688737154008, "ce": 6.17054591178894, "genuineness": 4.322831499576568, "identity": 0.5581885650753975, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.017946992814540864, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.08333008132963059, "target_raw": 0.14911001771688462, "ce": 6.282656679153442, "genuineness": 4.3770565414428715, "identity": 0.577014462351799, "wer": 0.011366836062488237, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 1.627802758910763, "target_raw": 1.052615792155266, "ce": 6.095845069885254, "genuineness": 4.061936511993408, "identity": 0.5063609171658754, "wer": 0.00463579898362507, "valid_fraction": 1, "identity_delta": -0.07065354518592358, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 0.43159179523134533, "target_raw": 0.4209970845282078, "ce": 6.271378116607666, "genuineness": 4.325467443466186, "identity": 0.5488957750797272, "wer": 0.004718614718614718, "valid_fraction": 1, "identity_delta": -0.028118687272071837, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 0.3406250109356503, "target_raw": 0.37296515330672264, "ce": 6.2575578784942625, "genuineness": 4.281033139228821, "identity": 0.5709965917468071, "wer": 0.0047619047619047615, "valid_fraction": 1, "identity_delta": -0.006017870604991913, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.09096678429569503, "ci95_z": [ -0.039072271920715586, 0.2362597442993796 ], "language_deltas": { "en": 0.24062499259197884, "de": 0.31884762572498426, "fr": -0.07485351449505624, "nl": -0.015869148270033745, "es": -0.013916034073397953 }, "languages_improved": 2, "clear_gain": false, "delta_ce": 0.01382023811340332, "delta_genuineness": 0.044434304237365725, "delta_wer": -4.329004329004321e-05, "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": -1.1962109636794176, "ci95_z": [ -1.549843798557815, -0.8305468968095671 ], "language_deltas": { "en": -0.5582031374789881, "de": -0.8950683533173994, "fr": -1.638378946894902, "nl": -1.3063476624123271, "es": -1.5830567182934718 }, "languages_improved": 0, "clear_gain": false, "delta_ce": 0.1755330467224121, "delta_genuineness": 0.26353093147277834, "delta_wer": 8.2815734989648e-05, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 1.7111328402403936, "ci95_z": [ 1.2386914098900723, 2.0932324746538438 ], "language_deltas": { "en": 0.8930175872913237, "de": 1.9208496046402603, "fr": 2.0046875474466117, "nl": 1.4691406249559047, "es": 2.267968836867867 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.1868116092681885, "delta_genuineness": -0.3151200294494629, "delta_wer": -0.006731037078863166, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 1.0, "reason": "No new configuration passes the held-out gates; retain standard fallback and inspect audio", "fallback_standard": true }, "reference_only": true, "updated": 1793043764.1799612 }, "rows": [ { "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": "0007b990eb60e588d11cd94f535637ad355b6b19aaba79e5b21c32309af38555", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25e2c67e77dbd93d8a88a11b36a8cf5513fc13352ee60a1e62f42b60250d077f", "generation_seconds_batch": 15.664619317045435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1319189071655273, "target_z": 3.671874924155974, "ce": 5.689021587371826, "genuineness": 3.760498285293579, "identity": 0.5833216905593872, "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_Triumph/0007b990eb60e588d11cd94f535637ad355b6b19aaba79e5b21c32309af38555.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "000eed729d5f903bb73fdb497b982e8eb58a4991c6c9bb2fc18a353e13a83171", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d2e3bee78acc3653b2471b4667c677cf336a90ec15d34f1a76e865613de25c69", "generation_seconds_batch": 16.57467593997717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44886744022369385, "target_z": 0.4843749453217486, "ce": 6.284721851348877, "genuineness": 4.570107460021973, "identity": 0.6727088093757629, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/000eed729d5f903bb73fdb497b982e8eb58a4991c6c9bb2fc18a353e13a83171.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "0079194b37a66e52b9349d50651948886bf745afd5190e8899290c218785b6e6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0d6995e1ea5bb9f14b41d0001a4d2d1672ae9ba28efd40b9b14a7077f0fafdf7", "generation_seconds_batch": 20.4297069250606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15701478719711304, "target_z": -0.06835938492145692, "ce": 6.173524379730225, "genuineness": 4.419482707977295, "identity": 0.5854073166847229, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Soel gelegd. Wanneer je klaar.", "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_Triumph/0079194b37a66e52b9349d50651948886bf745afd5190e8899290c218785b6e6.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "013e53ca6cbbeca8ef189b501264b6700b437fec7d5e4dfab26326687e33451c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3cddb14a3f59878bea7ce58c4526ca9342fbf7841c6d8088228a7b3a741376f5", "generation_seconds_batch": 15.015535069047473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.257392168045044, "target_z": 2.0156249417941194, "ce": 6.3641486167907715, "genuineness": 4.306513786315918, "identity": 0.3284738063812256, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/013e53ca6cbbeca8ef189b501264b6700b437fec7d5e4dfab26326687e33451c.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "01b45942cfeb998e7c5e8eff87b17303723bf3fb7f854b302349b5a2a2735279", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "38cc987144a373383bdae6b4756f740bd74345da638cec887b212318585ee8b5", "generation_seconds_batch": 15.85813246993348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9686333537101746, "target_z": 1.4687499753065962, "ce": 6.078212261199951, "genuineness": 4.099404335021973, "identity": 0.642549991607666, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/01b45942cfeb998e7c5e8eff87b17303723bf3fb7f854b302349b5a2a2735279.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "01b5f3762ba0dd56dfe0d7b80ec0740241b378724efdabbad1641da7557db4c2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ce1a55a477c7240ea74201a5bb9ab9fcb06e684365fc7aec93897f9380463ea", "generation_seconds_batch": 20.724042073008604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1534053087234497, "target_z": -0.0751953093030861, "ce": 5.613565921783447, "genuineness": 3.823258876800537, "identity": 0.2162594497203827, "hypothesis": "De deur staat nog open! Ik heb je jas op de stoel gelegd. Zeg maar wanneer ik 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_Triumph/01b5f3762ba0dd56dfe0d7b80ec0740241b378724efdabbad1641da7557db4c2.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "01b8c0c8771fba6bc2f55895f048ce5be0254e4ebfe531b6be2737fc8d270d16", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a9be7065d8d61ce697fde6df08829b13f169a232f87a7ca43a6d069e261c5ed5", "generation_seconds_batch": 21.575901863048784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.470179319381714, "target_z": 4.3125000493868075, "ce": 5.8875885009765625, "genuineness": 4.18726921081543, "identity": 0.13452032208442688, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/01b8c0c8771fba6bc2f55895f048ce5be0254e4ebfe531b6be2737fc8d270d16.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "01cfd4644f4342c2d31828755203c64ee40298cd21b81902ebf3490c74d6ddfa", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d55225e8142df84f794eb03baf7da3cb97bad8031f1108ff53cea11506d50a46", "generation_seconds_batch": 22.13236178108491, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14412377774715424, "target_z": -0.0927734287911656, "ce": 5.784333229064941, "genuineness": 3.6412534713745117, "identity": 0.5001602172851562, "hypothesis": "The 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_Triumph/01cfd4644f4342c2d31828755203c64ee40298cd21b81902ebf3490c74d6ddfa.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": "01e8ab7b0594c3417c2c0cf14280f9ef3e586fa0ead7873f30822430d7b6924a", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d68698306bb161ec1b79f679c07de7eb8f158488f727acc8c1018885351feea3", "generation_seconds_batch": 17.90328684495762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31892597675323486, "target_z": 0.23828121604656968, "ce": 6.268836498260498, "genuineness": 4.394378662109375, "identity": 0.5669956207275391, "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_Triumph/01e8ab7b0594c3417c2c0cf14280f9ef3e586fa0ead7873f30822430d7b6924a.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "7e53e43f2c01c3107f080c8f633858bea9e0b7aa121b73dd5f9f19ec0bcb1c3f", "generation_seconds_batch": 14.87799242301844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.121263027191162, "target_z": 1.7578124850075763, "ce": 6.109982967376709, "genuineness": 4.419482707977295, "identity": 0.722475528717041, "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_Triumph/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "022983cdf1366f414bf1910daa40e244abb8a776ca5aabf82d2c1bc9be4310a5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aa0549a4347fe1ea083035dcb3ff94f1d8cc99fb5c2c547040e5f2d7ffa258b3", "generation_seconds_batch": 20.697015449986793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8514103889465332, "target_z": 3.140625040567735, "ce": 5.744620323181152, "genuineness": 3.7416701316833496, "identity": 0.49056747555732727, "hypothesis": "De deur 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_Triumph/022983cdf1366f414bf1910daa40e244abb8a776ca5aabf82d2c1bc9be4310a5.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "0271b41d119d2a3f4c4f96f5cd476fea0f3f84fde42aa5511cd3296cbc461228", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "50f9644d5412690ca363c915dd7f21fd9f3a3bdf2d9d84a962d3add8cb72162a", "generation_seconds_batch": 14.799336500000209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4055536389350891, "target_z": 0.40234373985806626, "ce": 5.9431867599487305, "genuineness": 4.193545341491699, "identity": 0.7559544444084167, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0271b41d119d2a3f4c4f96f5cd476fea0f3f84fde42aa5511cd3296cbc461228.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": "03f867d766a81e02c56c8a94bb6f63b60f8369aee0a9a1bfcfd09271059a3663", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Someone moved the little blue chair.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6c22dffaa6da088499ce3f68e12025e04310c800eb73ed41705cd2aa40be3dd", "generation_seconds_batch": 19.227916516014375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0724497064948082, "target_z": -0.2285156238976159, "ce": 6.395919322967529, "genuineness": 4.281409740447998, "identity": 0.42329347133636475, "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_Triumph/03f867d766a81e02c56c8a94bb6f63b60f8369aee0a9a1bfcfd09271059a3663.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "0437eb722d21de7de71232f68b1b903dd5e1ae88e5d4dbc0e252b26e1b0bdc29", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "58259428e254e0f973366f4813f7e409d9f888e0437addcd979a86ffb51dc53f", "generation_seconds_batch": 14.841955462936312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29005011916160583, "target_z": 0.18359376455147014, "ce": 6.197352409362793, "genuineness": 4.482243061065674, "identity": 0.5015989542007446, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0437eb722d21de7de71232f68b1b903dd5e1ae88e5d4dbc0e252b26e1b0bdc29.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "04a94485b92b697da1e2e7c92cfc242466a6415bdde44cdc95ce790b2b1a1160", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d00b45a0569055cfd7254d8de18b8bc6f288eac28f22d4e40f45569328775edd", "generation_seconds_batch": 20.538122149999253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0146961212158203, "target_z": 5.3437503280695084, "ce": 6.284721851348877, "genuineness": 4.049196243286133, "identity": 0.19616734981536865, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/04a94485b92b697da1e2e7c92cfc242466a6415bdde44cdc95ce790b2b1a1160.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "04e769c40983ce7b8e61f9b6f9c7778ce5c88a32ca70faf352440ce158760f7b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6f4e096e6554cb4e8983f5c0fbf031c0bcdd7cb2d4a239b76fbe644f6d6ddb82", "generation_seconds_batch": 21.697298442944884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6386232972145081, "target_z": 0.8437500458591787, "ce": 5.863759994506836, "genuineness": 3.8922953605651855, "identity": 0.39223337173461914, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/04e769c40983ce7b8e61f9b6f9c7778ce5c88a32ca70faf352440ce158760f7b.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": "05377e0d67033a0538134e5a83018068988144b48e64c2a0f512f02bb5f7bbd8", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7434cf6e9ad49b852bc46116ce1e67614bb7dfc57010604b19394a469346e3b", "generation_seconds_batch": 15.49750205304008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.737626314163208, "target_z": 1.0312500246934038, "ce": 6.1894097328186035, "genuineness": 4.331617832183838, "identity": 0.6540815234184265, "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_Triumph/05377e0d67033a0538134e5a83018068988144b48e64c2a0f512f02bb5f7bbd8.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "05635a42ec31494fcb9d826bda5f2454b2d0cff227ad4fc0eb903cfb822a201a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2845dd7d62f75ef08cce952db36581be3fa00d20dea5c587ee4772254180edf6", "generation_seconds_batch": 21.76740474801045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5066192150115967, "target_z": 0.5937499611960796, "ce": 6.006728172302246, "genuineness": 3.9425034523010254, "identity": 0.5378425121307373, "hypothesis": "De deur staat nog open! Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/05635a42ec31494fcb9d826bda5f2454b2d0cff227ad4fc0eb903cfb822a201a.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "056f7398ab67e9a3083fb2153bdcfbdc18925e15538db4d5df3d04412fd8b7c0", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c904ffe358534d4e24315315fb66a0ea17b62123f9ff0f44f8a924c49000e586", "generation_seconds_batch": 21.076828069984913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43649208545684814, "target_z": 0.4609374902990199, "ce": 6.157639026641846, "genuineness": 4.005263805389404, "identity": 0.30509117245674133, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/056f7398ab67e9a3083fb2153bdcfbdc18925e15538db4d5df3d04412fd8b7c0.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "057be6f8f6182ab0cd5f5edf72d966b65090d2320f0686db7c299a5735c28171", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b24ede733bc2f54be7bcf58099e2c2dbc936dde6b496c01bb35be5cb9f66dd90", "generation_seconds_batch": 21.63453281694092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4553982019424438, "target_z": 2.39062489946257, "ce": 5.808161735534668, "genuineness": 4.042920112609863, "identity": 0.05771499499678612, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist!", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/057be6f8f6182ab0cd5f5edf72d966b65090d2320f0686db7c299a5735c28171.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": "058a988d6b6eabbe6086b6cdf7ace37366864099323ea49d2b957a1a9ca48f03", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The keys are on the kitchen table.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b42d5f59a18005de85e26dd33a0e65816459629ee4000de237b72e8a700ee55", "generation_seconds_batch": 19.10334942000918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.132521852850914, "target_z": -0.11474609931703972, "ce": 6.348263263702393, "genuineness": 4.1998209953308105, "identity": 0.33840444684028625, "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_Triumph/058a988d6b6eabbe6086b6cdf7ace37366864099323ea49d2b957a1a9ca48f03.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "f3b52d208319ea5a885e65c7c2c41eadfececcb223aaa6d3d58908200a15600a", "generation_seconds_batch": 14.984395907027647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23023578524589539, "target_z": 0.07031250617335097, "ce": 6.2767791748046875, "genuineness": 4.65797233581543, "identity": 0.551763653755188, "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_Triumph/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "0674a44c6261c04e489d4076ee29a7f22b0461b0b379f9686feb33be8b76bd9a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "05315d45efd61e3686288702fa652125a27f32bcda52ecd49288b673b171dbf3", "generation_seconds_batch": 19.901183816953562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13226403295993805, "target_z": -0.11523437963001322, "ce": 6.078212261199951, "genuineness": 4.419482707977295, "identity": 0.6877319812774658, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0674a44c6261c04e489d4076ee29a7f22b0461b0b379f9686feb33be8b76bd9a.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "082346a80948799b428458613f71ac101edf5b4fc0c2e1eee839bcea63a45087", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "18645d4469d9a2e79ae54f5305410f59094c6182d7e014b4fa2284dc4b80c733", "generation_seconds_batch": 19.607583576929756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5870591998100281, "target_z": 0.7460937574962119, "ce": 6.173524379730225, "genuineness": 4.068024158477783, "identity": 0.49586114287376404, "hypothesis": "De deur 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_Triumph/082346a80948799b428458613f71ac101edf5b4fc0c2e1eee839bcea63a45087.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "08311c37c854e741be16b45426e109c4a4671e39df0f4fc161453c678a31aeb3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cd05f635ffbe7cc92f65fcc4be10472e856699d8ceec23f7cb5dd251bf61a55d", "generation_seconds_batch": 17.549793955986388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6369037628173828, "target_z": 2.7343749171007157, "ce": 5.879645347595215, "genuineness": 4.042920112609863, "identity": 0.4365408420562744, "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_Triumph/08311c37c854e741be16b45426e109c4a4671e39df0f4fc161453c678a31aeb3.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "08639612f10898c85b6a73d88f4da19b64f4b3cf4ed7c367b25c3dbd8c0ff5af", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fa2875c6af7bcfbb8b505009ede42bb4dc76b6221e93e2025c1625cfb7dc6840", "generation_seconds_batch": 20.484057481051423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3381752967834473, "target_z": 4.062500077607841, "ce": 5.589737892150879, "genuineness": 3.9550557136535645, "identity": 0.4724830985069275, "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_Triumph/08639612f10898c85b6a73d88f4da19b64f4b3cf4ed7c367b25c3dbd8c0ff5af.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": "09af498d4ae3a24433736ce5b9b819964bc53b52a1cd3735e899f762ce1ee909", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Your message arrived after I had left.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "251edeedd61249f259f18cf2519c2da8cca3ce4e260d28b859e5729a5229d4cf", "generation_seconds_batch": 20.668166594929062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11524789035320282, "target_z": -0.14746093672833113, "ce": 6.475345611572266, "genuineness": 4.306513786315918, "identity": 0.5347015261650085, "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_Triumph/09af498d4ae3a24433736ce5b9b819964bc53b52a1cd3735e899f762ce1ee909.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "09df91dfee0e501274ed2ce562727091713cf4120fef3bb4f12eeb6ba327805c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0821cb881852c137fb76230388620f13b207cc62ad9c82d552bd932be282c41d", "generation_seconds_batch": 21.330106509034522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15598350763320923, "target_z": -0.07031250617335097, "ce": 6.165581703186035, "genuineness": 4.017816066741943, "identity": 0.5090251564979553, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/09df91dfee0e501274ed2ce562727091713cf4120fef3bb4f12eeb6ba327805c.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": "09ffd8fba1ee691b348de9ce901a9fcb2e312becbd5d60241b4595536ef8766c", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The road turns left behind the bridge.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "43751f7fbe391da92b5d450e1b5f9d21dd07d664dccd919f7b47e91edfde7ac2", "generation_seconds_batch": 15.583390384097584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3622398376464844, "target_z": 0.32031253439438395, "ce": 6.324435234069824, "genuineness": 3.6663577556610107, "identity": 0.5219941139221191, "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_Triumph/09ffd8fba1ee691b348de9ce901a9fcb2e312becbd5d60241b4595536ef8766c.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": "0a276e0d29e5f94ae4822a3dbae571d8f9772fa8807c71dce470ff6f2018384a", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65bfa9260bc7699645c7fdd3181936996a683b1145259d070a5c7b53862439fe", "generation_seconds_batch": 20.05473129102029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08740328997373581, "target_z": -0.2001953093030861, "ce": 6.41180419921875, "genuineness": 4.482243061065674, "identity": 0.5429346561431885, "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_Triumph/0a276e0d29e5f94ae4822a3dbae571d8f9772fa8807c71dce470ff6f2018384a.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "0aa5002430b58488d529d4620d9b0eac255e875364f1702941005a0b77d0b37e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5af685622490f3c054038f49b7406645aa995a7fa080501872ee299f94f53c1c", "generation_seconds_batch": 19.81654214602895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18537503480911255, "target_z": -0.01464843761023841, "ce": 6.078212261199951, "genuineness": 3.760498285293579, "identity": 0.41914287209510803, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0aa5002430b58488d529d4620d9b0eac255e875364f1702941005a0b77d0b37e.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "0afd4c45266e1e8dddbe4dfcc863f692ec52a9fb389083029dd3c73795ea3c4b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a31be0cdf0510326e9f73002ff98565555b991e6efe6c9f6f66b7c48cbb23f83", "generation_seconds_batch": 15.325928542995825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5004315376281738, "target_z": 0.5820312336847153, "ce": 5.95112943649292, "genuineness": 3.9550557136535645, "identity": 0.8148291707038879, "hypothesis": "De deur staat nog open! Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0afd4c45266e1e8dddbe4dfcc863f692ec52a9fb389083029dd3c73795ea3c4b.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": "0b05e3ec00a60824a3432fc19ba9fc5fbb95a3d549de0cc518d6ffed78c895de", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "408bd64096795658c77ab3f86f5223fa43e69fde85aa1ed983aba95e43148b8d", "generation_seconds_batch": 15.712868474889547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9174124002456665, "target_z": 3.2656250264572186, "ce": 5.998785495758057, "genuineness": 4.231201171875, "identity": 0.49041783809661865, "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_Triumph/0b05e3ec00a60824a3432fc19ba9fc5fbb95a3d549de0cc518d6ffed78c895de.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "0b2a84ac49cad387e3ea3ae6329eb22b2c8be08a9fb8c200e4f1afba5969c037", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c88d2d680a06216cfcf7f8baa141c2433feb9b75f54204b6cd82b6cb6579c775", "generation_seconds_batch": 21.453167006955482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.438897728919983, "target_z": 2.359374959432265, "ce": 5.478540420532227, "genuineness": 4.074300289154053, "identity": 0.319410502910614, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0b2a84ac49cad387e3ea3ae6329eb22b2c8be08a9fb8c200e4f1afba5969c037.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "0ba075abb0abb01eed9a340fd41dbc7b1f62b93951094eccbf28e22908fa69ea", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "925eb7f7b8687332b8be62cc259098a41efccd4ef1070317edddd801f0104df8", "generation_seconds_batch": 20.24716511601582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3481450080871582, "target_z": 2.1875000634973243, "ce": 6.149696350097656, "genuineness": 4.218649387359619, "identity": 0.5375536680221558, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0ba075abb0abb01eed9a340fd41dbc7b1f62b93951094eccbf28e22908fa69ea.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": "0bb6d0a77392ed99b740b8f96c4f2b171688073db5e777357d890e73b6f3f75f", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca5712590f6afe538ff3d234d0af457775f284287156a691633ebbedbdae9c1a", "generation_seconds_batch": 20.445791154983453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38080286979675293, "target_z": 0.355468716928477, "ce": 6.4515180587768555, "genuineness": 4.444586753845215, "identity": 0.5267207622528076, "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_Triumph/0bb6d0a77392ed99b740b8f96c4f2b171688073db5e777357d890e73b6f3f75f.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "0bbca733878002bc36fe5ea3131017211aa2add19e7aed89f392371558edaf17", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1c11198d6ad06e48167a755e4f5205b5808c58cffe110bb021e8c52bba7b17f6", "generation_seconds_batch": 14.824545283918269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15031147003173828, "target_z": -0.08105467305876828, "ce": 6.157639026641846, "genuineness": 4.218649387359619, "identity": 0.5112448334693909, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0bbca733878002bc36fe5ea3131017211aa2add19e7aed89f392371558edaf17.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "0bd31d33612f4d378f1b20c2464170c91d08510d597ec6f4a78b7e7237ee8c7d", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "adcb78d948540ff78813a46a4470bb386108c585f8fab0801a62b7e734f58b00", "generation_seconds_batch": 16.42231657006778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1374204456806183, "target_z": -0.10546874514950995, "ce": 6.284721851348877, "genuineness": 4.432034492492676, "identity": 0.15988725423812866, "hypothesis": "De deur 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_Triumph/0bd31d33612f4d378f1b20c2464170c91d08510d597ec6f4a78b7e7237ee8c7d.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "0c026251e38d09c5535261576df788e75aca87a0328d78276ec0c2618157e834", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f60e83e3b059236bdf41c4090b55675d24fb5289dbc600b3f8fed74decfdb527", "generation_seconds_batch": 14.712841668981127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4303044080734253, "target_z": 0.4492187627876556, "ce": 6.141753673553467, "genuineness": 4.362998008728027, "identity": 0.7586778402328491, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0c026251e38d09c5535261576df788e75aca87a0328d78276ec0c2618157e834.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "0c4f90c78eddb984921f7075560b2877a0488d479e18eeeb732bf99656da75e9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "caa766e564c2dab7e8c90c0505c6591d493e648844fc26cee8b800d193835033", "generation_seconds_batch": 19.92561770300381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2120157480239868, "target_z": 1.929687380942517, "ce": 6.133810997009277, "genuineness": 4.15588903427124, "identity": 0.5686684250831604, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0c4f90c78eddb984921f7075560b2877a0488d479e18eeeb732bf99656da75e9.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "5e542a024b67743bd0b601f356d094cacaed642c79c95191c8950969cff698ba", "generation_seconds_batch": 14.816853134892881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.036354854702949524, "target_z": -0.29687499470855633, "ce": 6.197352409362793, "genuineness": 4.231201171875, "identity": 0.5980076789855957, "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_Triumph/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "0cbaace9b619d6b9fede059f590fb593876907bafdc653a887612ad22d3acb0f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8998f30be18c73a8a21803f9673f0ec8393d09eb7a5a6ee9b04ef9fd86fabbf5", "generation_seconds_batch": 20.72033326898236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7524073123931885, "target_z": 2.9531249488493776, "ce": 6.348263263702393, "genuineness": 4.7081804275512695, "identity": 0.6963431239128113, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0cbaace9b619d6b9fede059f590fb593876907bafdc653a887612ad22d3acb0f.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "0cd786dfcd6ef95ff30972a1b70935555f30f0ef52c4a429d57d766bb682ad86", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f12c061bfa20c08bf81f3715409d168ed76673b47926833d813a924546f4a2d7", "generation_seconds_batch": 21.761646850965917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6186840534210205, "target_z": 4.593750412732607, "ce": 5.8875885009765625, "genuineness": 3.986435890197754, "identity": 0.4754858613014221, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0cd786dfcd6ef95ff30972a1b70935555f30f0ef52c4a429d57d766bb682ad86.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "0d091e0b2161bcec211f32a517e756ee7316384d9609200e27264906b94ffee3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7014d283d27a0bbebbc35c54ed960ad5518515763f6938da643959ef823ddbf5", "generation_seconds_batch": 14.869461063994095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7029057741165161, "target_z": 2.859374902990199, "ce": 5.7128496170043945, "genuineness": 4.017816066741943, "identity": 0.46615904569625854, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0d091e0b2161bcec211f32a517e756ee7316384d9609200e27264906b94ffee3.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "0d48fe6e2c096d94038040445898cb09187598000e00937737b9f539456d3089", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "65a4ddd72163f47dd95abd8d736d7020f9826880c18aaaecbdc703f1fa87368b", "generation_seconds_batch": 21.819705490022898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2575647532939911, "target_z": 0.12207033223267542, "ce": 5.728734970092773, "genuineness": 3.6287014484405518, "identity": 0.23712041974067688, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0d48fe6e2c096d94038040445898cb09187598000e00937737b9f539456d3089.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "0de0b6ae98f1f24912b86e9a88dcc4d08e5aff135bf5e722e4d836c70683a8ae", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f6161d1d7523f431d45a8a11f0b42792f4142a9116c132d6ea2aed888854601f", "generation_seconds_batch": 20.918549834983423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18898451328277588, "target_z": -0.007812513228609218, "ce": 6.332377910614014, "genuineness": 4.7458367347717285, "identity": 0.6576448678970337, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0de0b6ae98f1f24912b86e9a88dcc4d08e5aff135bf5e722e4d836c70683a8ae.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "0ed1acfda94bf700c297a0e59ce933464107c4374c39b32dba255543eca7931b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e34342bf3b507f5ee40bd9a998948f16bdc0862e5f2fb972d09fdc992952f709", "generation_seconds_batch": 21.819705490022898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38492801785469055, "target_z": 0.3632812583781192, "ce": 5.935244083404541, "genuineness": 3.8546390533447266, "identity": 0.21856454014778137, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0ed1acfda94bf700c297a0e59ce933464107c4374c39b32dba255543eca7931b.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "0f279531f2f6f7b55a1e05be6726fb84e3587d60157b7ce2c0629d111c86a59e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cc0fc9660a798d18e835361a81ab2d204069c0e5e44f107b28d7c666077db122", "generation_seconds_batch": 19.350619814009406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12298250198364258, "target_z": -0.13281249911809273, "ce": 6.062326908111572, "genuineness": 4.425758361816406, "identity": 0.6817173957824707, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0f279531f2f6f7b55a1e05be6726fb84e3587d60157b7ce2c0629d111c86a59e.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "0fda7084579b345f6b5c75f1d8176648e4f6f6e4cee226987fe67a39f729179f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "959bdd69576ae72674742fb1eb9513602e583204af5f8c117698973084f4a942", "generation_seconds_batch": 21.25957598804962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1542640924453735, "target_z": 1.82031259083645, "ce": 5.903473377227783, "genuineness": 3.898571252822876, "identity": 0.5850682854652405, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0fda7084579b345f6b5c75f1d8176648e4f6f6e4cee226987fe67a39f729179f.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "0fef81d504528432d53c6a12ec5a8be07d80afe2bf7fcb31dc9715aa34060358", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f36978b17f87292ef31b8dbcaa0a7de5408f3e2f9eca259647048747242a331b", "generation_seconds_batch": 16.71561454399489, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.734187364578247, "target_z": 4.812499992944741, "ce": 6.1894097328186035, "genuineness": 4.068024158477783, "identity": 0.3519570231437683, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/0fef81d504528432d53c6a12ec5a8be07d80afe2bf7fcb31dc9715aa34060358.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "10178aff5b8d282268024a951369c068f9a74cc0043fb0cd17fcdc8f504732c7", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3eaa70049d873257d2786983e1bd7ac363c293b6ce8ab6f874581a1eaa690ae8", "generation_seconds_batch": 22.10802744200919, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0494165420532227, "target_z": 3.5156252240044497, "ce": 5.708878040313721, "genuineness": 3.9299514293670654, "identity": 0.6097437143325806, "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_Triumph/10178aff5b8d282268024a951369c068f9a74cc0043fb0cd17fcdc8f504732c7.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "104fe0ea7a918a0312535690487e57d288d8a368d80ef909ce17da603b72c168", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "44b3d2cd111c922fc226a45004a67b0345fa11399e989e590b30d938c93d343f", "generation_seconds_batch": 14.824545283918269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17789824306964874, "target_z": -0.028808594907503305, "ce": 6.062326908111572, "genuineness": 4.042920112609863, "identity": 0.5313844680786133, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/104fe0ea7a918a0312535690487e57d288d8a368d80ef909ce17da603b72c168.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "10b0d53363852d26533ea92f7e6ee3aa28cc31c39f2f94ab7245ca75988f9a3e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "39a82998384b24774a93c4c4545ae273f4b1929d5c1469e0711db85bfe05843c", "generation_seconds_batch": 20.330683349980973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5691823959350586, "target_z": 4.500000141105165, "ce": 6.372091293334961, "genuineness": 4.162164688110352, "identity": 0.4289729595184326, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/10b0d53363852d26533ea92f7e6ee3aa28cc31c39f2f94ab7245ca75988f9a3e.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "10bb910389a4e87e9a131072ef23213ae8cea0897ea04d4eb8185ece44672ef1", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e5edfec015e6b9c5fca47c554e9f1fd1dd0328f9305a3347f76adfd2bd3fd044", "generation_seconds_batch": 22.98101162200328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2585960328578949, "target_z": 0.12402345348456947, "ce": 6.300607204437256, "genuineness": 4.469690799713135, "identity": 0.5882184505462646, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/10bb910389a4e87e9a131072ef23213ae8cea0897ea04d4eb8185ece44672ef1.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "1256738c231fb3da991bcaf47b49db784b46dca8bfcbbed5ff54da215ef5a00c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "765181875c9c971fa4df994f24ea67b8faa056a8b35536d2b0e6bf7588b4c4f9", "generation_seconds_batch": 19.311582899070345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1271076202392578, "target_z": -0.1250000141105165, "ce": 6.117925643920898, "genuineness": 4.193545341491699, "identity": 0.6294931769371033, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1256738c231fb3da991bcaf47b49db784b46dca8bfcbbed5ff54da215ef5a00c.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "12a4a769a951b327880f95b18c497dbf883412f9c38a503c9f50a0e6eed7b392", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8d396be5e3bd55342f225ab2031bf30318e1e4137570ec3d31e35fbf88ec8c5e", "generation_seconds_batch": 21.04703793709632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.737626314163208, "target_z": 1.0312500246934038, "ce": 6.022613525390625, "genuineness": 4.381826400756836, "identity": 0.6093131899833679, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/12a4a769a951b327880f95b18c497dbf883412f9c38a503c9f50a0e6eed7b392.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "ea36e0a561c46551934d7f585b1e25a1c79614adcedb78a132f3330ee4fd4055", "generation_seconds_batch": 14.770697762956843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2611742317676544, "target_z": 0.1289062566143046, "ce": 6.372091293334961, "genuineness": 4.406930446624756, "identity": 0.7657427787780762, "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_Triumph/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "12b721ded090c43ab9088623fbc3eed47e608f5cec40e1aa5578841c8128cd3f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8783b198f31ae9cbf646716da2e5ed38bad300d864e24959a7db11a58c3a8360", "generation_seconds_batch": 19.467257536947727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6283104419708252, "target_z": 0.8242187204561061, "ce": 5.736677646636963, "genuineness": 3.9550557136535645, "identity": 0.36031481623649597, "hypothesis": "De deur 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_Triumph/12b721ded090c43ab9088623fbc3eed47e608f5cec40e1aa5578841c8128cd3f.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "12fe13a3369730c9f917469f65ed21a4580cb35cc5f1a83725a3edbe433c21e9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0964e43a94749dc5d483dd39e948e78332845af4b05a2b74c5aa52cc835bf634", "generation_seconds_batch": 21.48318639001809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3563952445983887, "target_z": 2.203125033512477, "ce": 6.0305562019348145, "genuineness": 4.231201171875, "identity": 0.3892049491405487, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/12fe13a3369730c9f917469f65ed21a4580cb35cc5f1a83725a3edbe433c21e9.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "1370ea68cd2ddd663d37b790c3a313a8e1e06d4a61329a4dc784faff60da594e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ff8652acd553300cacd50b57e633dc8aad1ad33ff6ff7e1387501359e88c9909", "generation_seconds_batch": 19.26809847599361, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20909450948238373, "target_z": 0.03027343584642385, "ce": 6.109982967376709, "genuineness": 4.432034492492676, "identity": 0.6849642992019653, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1370ea68cd2ddd663d37b790c3a313a8e1e06d4a61329a4dc784faff60da594e.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "1389a8522239af1ec3f23373fac0d068619c623ea128af6249f601394df3c800", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a39047d08b2de61f7b4920e24f9dbc85799acc4e0b772dcbe5184f329f892676", "generation_seconds_batch": 19.3628157050116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4303044080734253, "target_z": 0.4492187627876556, "ce": 5.542081832885742, "genuineness": 3.773050308227539, "identity": 0.3954640030860901, "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_Triumph/1389a8522239af1ec3f23373fac0d068619c623ea128af6249f601394df3c800.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "13bc38ff6d1e099a10a441e82250ba24e5e0b056750df25ea8075039563ff9c2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "03607aaf509bbb95c8f19a6560e03e7929ee76ea1c0a6b90ff8fe38253401b83", "generation_seconds_batch": 20.735107426997274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4199915826320648, "target_z": 0.42968749382664906, "ce": 5.6334228515625, "genuineness": 3.9676074981689453, "identity": 0.6735388040542603, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/13bc38ff6d1e099a10a441e82250ba24e5e0b056750df25ea8075039563ff9c2.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "1419ff2eb485ee83d5c7e213304a6397e908472965ca947896d19bd9d78d9614", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6c4cb4c0dd2d1c0e65b50407c7c92312e8a1a0448b63264c00bceca40bc7291c", "generation_seconds_batch": 21.49624779797159, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6021833419799805, "target_z": 4.562500021165775, "ce": 6.348263263702393, "genuineness": 3.961331605911255, "identity": 0.3667716085910797, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1419ff2eb485ee83d5c7e213304a6397e908472965ca947896d19bd9d78d9614.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": "146a29e7e2f692640ee5aec0a623030157bcedd9eeec4550d3e80184dd5632cc", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Escribí el número en el sobre.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a9bf58d30741ea7a1f4e8d9a08284b88467a6909d70e0d00c566524d4fb4f1bd", "generation_seconds_batch": 20.55057956604287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9669139385223389, "target_z": 3.359375072316397, "ce": 6.24500846862793, "genuineness": 4.319066047668457, "identity": 0.6388378739356995, "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_Triumph/146a29e7e2f692640ee5aec0a623030157bcedd9eeec4550d3e80184dd5632cc.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "14a253e069f0dd9b0d73b045a62c2d6f1e0d6d63fca68e9dee08fa2bd50564fa", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "906907b252b995c0599cde98dfceada1f025a4dc4c965967e6fcc459958fb7ae", "generation_seconds_batch": 14.890676548937336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4859936237335205, "target_z": 0.5546875361581985, "ce": 6.1020402908325195, "genuineness": 3.9299514293670654, "identity": 0.5951828956604004, "hypothesis": "De deur 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_Triumph/14a253e069f0dd9b0d73b045a62c2d6f1e0d6d63fca68e9dee08fa2bd50564fa.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "154324a1424cdf51a096efa296b6cdf1a0665ce5cda9899fdcff16d995092655", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d70c50855c60f9ad9829cb8431e505eec1939f5a398d18fb8e78c253cb5c914c", "generation_seconds_batch": 23.306978077976964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.156669855117798, "target_z": 3.718750285737959, "ce": 5.411027908325195, "genuineness": 3.735394239425659, "identity": 0.06117403507232666, "hypothesis": "De deur 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_Triumph/154324a1424cdf51a096efa296b6cdf1a0665ce5cda9899fdcff16d995092655.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "90d252bc7cea3bea5227c57acdd6fde4f12d2bbd4ef4dbc6d5a8af8ee44e91f5", "generation_seconds_batch": 16.880567817017436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033261001110076904, "target_z": -0.3027343866852715, "ce": 6.23706579208374, "genuineness": 4.394378662109375, "identity": 0.6710584163665771, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zum kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "157ace9e4981cc8cba62b4bbbfda03f043cd841c3ea4cd1842452cf105dc4c86", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "efc02250c2e24ba6f09d3acf8a22868cd136585fd278b354f5084f91e7f26c50", "generation_seconds_batch": 22.396641165949404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.214421510696411, "target_z": 3.828125075844026, "ce": 6.0305562019348145, "genuineness": 3.986435890197754, "identity": 0.5997120141983032, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/157ace9e4981cc8cba62b4bbbfda03f043cd841c3ea4cd1842452cf105dc4c86.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "157b572fe4bbdb5be0494fbb7d9bef94c2c3deae7eb09cb818727d769427957f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a27308c1e02ea6c57fe4c514405125d01c831f6879138fb7014217b3914c23d7", "generation_seconds_batch": 14.710360034951009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3612067699432373, "target_z": 6.000000423315495, "ce": 5.879645347595215, "genuineness": 4.030367851257324, "identity": 0.24777011573314667, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/157b572fe4bbdb5be0494fbb7d9bef94c2c3deae7eb09cb818727d769427957f.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "158f92d6ac46fd5a70a2c2e3770211b3c9283b444105f91a39f0246d1d242cb9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be24be962fe732c18ac301404eb598ae427646c496a12f3a57ea679b8af37831", "generation_seconds_batch": 19.963971807039343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3137695789337158, "target_z": 0.2285156097870994, "ce": 6.046441555023193, "genuineness": 3.8295347690582275, "identity": 0.4389169216156006, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/158f92d6ac46fd5a70a2c2e3770211b3c9283b444105f91a39f0246d1d242cb9.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": "15b992b939df44a9361ebd0bcf23dc60f1cfb311cdb65cd60ce93c1b9718bbad", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dbe8e67a3e6583dfe9ec0bdd751e4ad1a3ab0613ef2232af5a18bd029cb084e6", "generation_seconds_batch": 15.162730304989964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.219407320022583, "target_z": 0.049804676586397395, "ce": 5.839932441711426, "genuineness": 3.6412534713745117, "identity": 0.5961734056472778, "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_Triumph/15b992b939df44a9361ebd0bcf23dc60f1cfb311cdb65cd60ce93c1b9718bbad.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": "15cfd0174d383097a924476b8f445569259f384828363f84ed5dcbe0ef2ed1ac", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7bc7eac48aeb6cd5c6ffcec3c115cfe94a542fec69432e7d8d80dd2f0a076f11", "generation_seconds_batch": 15.133425218984485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21450874209403992, "target_z": 0.040527350639900636, "ce": 6.09409761428833, "genuineness": 4.111956596374512, "identity": 0.6424477100372314, "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_Triumph/15cfd0174d383097a924476b8f445569259f384828363f84ed5dcbe0ef2ed1ac.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "15d871ff3b718c4e81bb61011bc14e0b901d6ee08e1195393880d3f68ec66478", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5de5cba77340d733b8d9fceb49da3423af04d768c77867e91b6483b4b1be1d56", "generation_seconds_batch": 20.876751233940013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1974925994873047, "target_z": 0.008300793541582733, "ce": 6.109982967376709, "genuineness": 4.13078498840332, "identity": 0.5503446459770203, "hypothesis": "De deur 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_Triumph/15d871ff3b718c4e81bb61011bc14e0b901d6ee08e1195393880d3f68ec66478.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "16484eb5c1aa76f155d0c5f269503b79ede529b8af1ed3ae3962086bedd4ef67", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a697fe4d90e26b52bab18f65561bc51360786bfd61ddf4a6ab70eef9543d2849", "generation_seconds_batch": 21.642533783917315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2549865245819092, "target_z": 0.11718747266087429, "ce": 5.498397350311279, "genuineness": 3.7918784618377686, "identity": 0.5623533725738525, "hypothesis": "The 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_Triumph/16484eb5c1aa76f155d0c5f269503b79ede529b8af1ed3ae3962086bedd4ef67.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": "16fc29047bb2253a3803c2dbc3011b0a62201d861a9f1728fa868794288a1c06", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1672b4a3c23af3a5bcee749843733f925bba4932578b2b804d53599fc504e7ef", "generation_seconds_batch": 21.44198712706566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08173123747110367, "target_z": -0.2109375044095364, "ce": 6.141753673553467, "genuineness": 4.595211505889893, "identity": 0.793756365776062, "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_Triumph/16fc29047bb2253a3803c2dbc3011b0a62201d861a9f1728fa868794288a1c06.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "17b6ce36808d9ae2d07b96a0bff3f5c28e7d993a8ad932e1aac7a91fa78094fa", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bc212118bab62c69b1ddd740376010bfb997db55f846b4c6b652823443c1d7dd", "generation_seconds_batch": 19.92561770300381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9892590045928955, "target_z": 1.5078125132286093, "ce": 6.348263263702393, "genuineness": 4.143336772918701, "identity": 0.3453604578971863, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/17b6ce36808d9ae2d07b96a0bff3f5c28e7d993a8ad932e1aac7a91fa78094fa.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "17e3b6eb7ec4d3f973ae92360018a88c5cb1624719fc0a80a1766cf2f31a83ea", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "fd7d36d0ef7f6c142468f8d0ca6c605af3bbf49cb691c5a7fd40f6ca0860c34f", "generation_seconds_batch": 20.85403460590169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3051743507385254, "target_z": 4.000000197547231, "ce": 5.3792572021484375, "genuineness": 3.835810661315918, "identity": 0.6358819603919983, "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_Triumph/17e3b6eb7ec4d3f973ae92360018a88c5cb1624719fc0a80a1766cf2f31a83ea.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "180c8a451ec3600d7417df900626c2a4531f15e5cab32dcd73447318b22801c3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1a3fc28b3aa5a8993ce0827aa17815e89314f236425288f67c65052ad2c8be7d", "generation_seconds_batch": 19.08969504397828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10029430687427521, "target_z": -0.17578125132286093, "ce": 6.181467056274414, "genuineness": 4.6956281661987305, "identity": 0.6288079023361206, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/180c8a451ec3600d7417df900626c2a4531f15e5cab32dcd73447318b22801c3.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "18a8befecadfd01a69ec55d7a12b622836be765f4e95ad75342142631a41cb62", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3d727fa37765ed95f1105085eb227b64b09b0711a9844b82aafeacbac3db5209", "generation_seconds_batch": 21.76740474801045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2168291211128235, "target_z": 0.04492187345666226, "ce": 5.458683967590332, "genuineness": 3.760498285293579, "identity": 0.5382611751556396, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/18a8befecadfd01a69ec55d7a12b622836be765f4e95ad75342142631a41cb62.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "19452abd52100ae00b0fbca33bcf74e170f32a16d25499907fa91a5fe9467280", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9f946538649b2094392611dd8e715af2d210b33e38aef86c0f0f42c9b6d42ac7", "generation_seconds_batch": 19.684224909055047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0992630273103714, "target_z": -0.17773437257475497, "ce": 6.24500846862793, "genuineness": 4.381826400756836, "identity": 0.7460683584213257, "hypothesis": "Niet. Ik heb het 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_Triumph/19452abd52100ae00b0fbca33bcf74e170f32a16d25499907fa91a5fe9467280.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": "1977252ab321329f7d51689289f167072538ebc5e09963b0882f0fc21093e58c", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "36e7dcc15a39b06dde5e21f14fbbd9ebf8fe9124531d84dcb732540093440267", "generation_seconds_batch": 18.485136258066632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.57674640417099, "target_z": 0.7265625449772714, "ce": 6.41180419921875, "genuineness": 4.268857479095459, "identity": 0.44669240713119507, "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_Triumph/1977252ab321329f7d51689289f167072538ebc5e09963b0882f0fc21093e58c.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "19d635b8106d33158a2325b2cdfe5c1040f57eb938096ea7e1bcadf09bdbd7ef", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a056341d7337f4ccf1f51c5f11e8dfc2d3ecd90cd51408011f6db248099f6fb7", "generation_seconds_batch": 19.238406587042846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23023578524589539, "target_z": 0.07031250617335097, "ce": 6.268836498260498, "genuineness": 4.65797233581543, "identity": 0.44580042362213135, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/19d635b8106d33158a2325b2cdfe5c1040f57eb938096ea7e1bcadf09bdbd7ef.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "19e51c687b16b6da189d88e55f345fca68d301254b818c9f4a1fe0aea6c33eec", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c680afb9d85386c0333fcfbe00b90bb32d73c567cadad9bf12c3b395124ad75", "generation_seconds_batch": 21.453167006955482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6616545915603638, "target_z": 2.781250052914437, "ce": 5.764476776123047, "genuineness": 4.093128204345703, "identity": 0.4174290895462036, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/19e51c687b16b6da189d88e55f345fca68d301254b818c9f4a1fe0aea6c33eec.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "1a04d1dc4c329c27edc6981843a28ad40ac932e0eed14d909a0aead0cee97ea0", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "828404bff6bc769a599373a006f710ce38d68ad1b0f94c8ffdf28057ec311cf1", "generation_seconds_batch": 19.721552208065987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5691823959350586, "target_z": 4.500000141105165, "ce": 6.324435234069824, "genuineness": 4.18099308013916, "identity": 0.5897126197814941, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1a04d1dc4c329c27edc6981843a28ad40ac932e0eed14d909a0aead0cee97ea0.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "1a409c3ab988096ef253a73a44b8091e68c9357a945f355842c134487a7751e6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "479558bbc24e07f7140b0320587dd9f59ed4725899c0f2f8a12bb4b6310120be", "generation_seconds_batch": 19.395880938973278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7706273198127747, "target_z": 1.0937500176381456, "ce": 6.173524379730225, "genuineness": 4.7081804275512695, "identity": 0.5464086532592773, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1a409c3ab988096ef253a73a44b8091e68c9357a945f355842c134487a7751e6.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "1a4be168313b5775c65593f8f178dd83830b12c714b65a3927e9079aa2a06247", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "89252727a9397405f3a6a4fecf5d9193863fd84f114741401f6bda0150dbfbad", "generation_seconds_batch": 14.248142100055702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3251136839389801, "target_z": 0.25, "ce": 6.109982967376709, "genuineness": 4.105680465698242, "identity": 0.45075687766075134, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1a4be168313b5775c65593f8f178dd83830b12c714b65a3927e9079aa2a06247.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "1a65760fa3b136caf6bc01c4428ef799cd7e2212c86634920bba04ecf7415984", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "854ec079a8435300b8a0cb66ea7e46d95d7896ea02a9100a84a501e9ef243b10", "generation_seconds_batch": 22.28774522000458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4636484384536743, "target_z": 2.4062498694777226, "ce": 6.332377910614014, "genuineness": 4.432034492492676, "identity": 0.40908631682395935, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1a65760fa3b136caf6bc01c4428ef799cd7e2212c86634920bba04ecf7415984.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": "1a6e7c50f73cc96c319f156a95dd8bdf68e098a3ebb875af99bb108c98b6e939", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Your message arrived after I had left.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1e91a2aaabac36b04e0bf03a96ec459d6aedaa37cffcc1e008006f60b5dc5b5", "generation_seconds_batch": 16.68674348294735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11060712486505508, "target_z": -0.15624999647237087, "ce": 6.348263263702393, "genuineness": 4.093128204345703, "identity": 0.3484402894973755, "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_Triumph/1a6e7c50f73cc96c319f156a95dd8bdf68e098a3ebb875af99bb108c98b6e939.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "1ad520b4afaafba3ef5dfebae07107278970f5675ba953c51cbd5e68b0ae8938", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8ff4705e6c3e3817c24339d7906c303f5be2b480c3b290353ed8cfc3b83ad63a", "generation_seconds_batch": 21.669141376041807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11988865584135056, "target_z": -0.13867187698429137, "ce": 6.1894097328186035, "genuineness": 3.6789097785949707, "identity": 0.3051920533180237, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1ad520b4afaafba3ef5dfebae07107278970f5675ba953c51cbd5e68b0ae8938.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "1ad8f025dd919b9e3a18d6e1071dd0c3fdb78a13aee6c1121668e35d18378f19", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "61aca33b24df5ebf670878ddc7d72c596a7f4074356f9877e4b1c740fae901c1", "generation_seconds_batch": 21.4669050819939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41174131631851196, "target_z": 0.4140624673694306, "ce": 6.332377910614014, "genuineness": 4.281409740447998, "identity": 0.31988224387168884, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1ad8f025dd919b9e3a18d6e1071dd0c3fdb78a13aee6c1121668e35d18378f19.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "1aeb8ffe7e415d621ff8497f3f0227bd03da1014267019a993c037c932019b09", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "db9d315baf5e80c79613d82579e341d293f9bbcb90a52658f6c30216957bd999", "generation_seconds_batch": 16.32297155004926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09101277589797974, "target_z": -0.1933593708109404, "ce": 6.252951145172119, "genuineness": 3.9048471450805664, "identity": 0.4255978465080261, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1aeb8ffe7e415d621ff8497f3f0227bd03da1014267019a993c037c932019b09.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": "1af48379e1c59260354a703b77898c55b1fcb21e7eef7f6af0d25cdb85662e8c", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87678b353569ecb829cc9504f27f62cae760c4aab21f986cfc850e07921abfae", "generation_seconds_batch": 20.05473129102029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07915303856134415, "target_z": -0.21582030753927153, "ce": 6.467403411865234, "genuineness": 4.425758361816406, "identity": 0.5916211605072021, "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_Triumph/1af48379e1c59260354a703b77898c55b1fcb21e7eef7f6af0d25cdb85662e8c.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "1b142ee4b689ba4947edc21165c0c55c66f749c4709913dd6ffd8df4ca0cb9dd", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "07cd734dd7f0c046e0c5416fdfe9de0a39364c7019b299feff9485f688f22daa", "generation_seconds_batch": 23.373311821953394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2307514250278473, "target_z": 0.071289066799298, "ce": 6.149696350097656, "genuineness": 3.9801597595214844, "identity": 0.5141342878341675, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1b142ee4b689ba4947edc21165c0c55c66f749c4709913dd6ffd8df4ca0cb9dd.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "1b6f0c9226fc995df167eb7346937dc2fc1bfa3fb610464db68cadb845537524", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d6e347dc917aab957a505b8b90c7f6d0ec740e9d2c765e9d55e65bfb25d4e7bb", "generation_seconds_batch": 19.737997381947935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3381752967834473, "target_z": 4.062500077607841, "ce": 6.427689552307129, "genuineness": 4.193545341491699, "identity": 0.6098658442497253, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1b6f0c9226fc995df167eb7346937dc2fc1bfa3fb610464db68cadb845537524.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "1b7ba3fd6fd8dcdfe74365d22988409383ff4d6fbd89036b907841330ef88f1f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e48c55d54a52e810801b7a326ba14a04e53b602d3f7680705a7a014e3bcdf3ee", "generation_seconds_batch": 21.91700855595991, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.833190441131592, "target_z": 5.000000084663099, "ce": 5.919358730316162, "genuineness": 3.860914945602417, "identity": 0.49212947487831116, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1b7ba3fd6fd8dcdfe74365d22988409383ff4d6fbd89036b907841330ef88f1f.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "1c2098b12c3d58ff5006254b54c08bb2ade9ace02ef880efc0723c20c1fc79e0", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a5aa40e80dc45f59daa9b9bf976160c9e4784afc8a217b8ec40ae79051cd1984", "generation_seconds_batch": 15.786689779954031, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25086140632629395, "target_z": 0.10937498765329806, "ce": 6.284721851348877, "genuineness": 4.287685871124268, "identity": 0.6746623516082764, "hypothesis": "Yang zei, ik heb het kleine doosje gevonden. Het stond naast het oude ram. We kunnen er samen in kijken.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1c2098b12c3d58ff5006254b54c08bb2ade9ace02ef880efc0723c20c1fc79e0.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": "1c92485780b634e76321dded24ca3ebcd5bde28d74c7207737553b763a691d78", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Escribí el número en el sobre.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c57e1f8267663abe7a64eb1a4c7ae947e62b56b80bfa8fbfd15f25e903bc5a2", "generation_seconds_batch": 14.598500501946546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9156930446624756, "target_z": 5.156250236351151, "ce": 6.260893821716309, "genuineness": 4.1998209953308105, "identity": 0.621167778968811, "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_Triumph/1c92485780b634e76321dded24ca3ebcd5bde28d74c7207737553b763a691d78.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "1cb1a8298bb873c49bb0f4ae4225b4496fb35c92d0f7d991bb5063587b5908a6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2ee1aeede9a22e0398a1b23229557fcdd8b94b5b7d0df8241e582bf2f8dcb60e", "generation_seconds_batch": 19.504834538907744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5623084306716919, "target_z": 0.6992187345666225, "ce": 6.356205940246582, "genuineness": 4.65797233581543, "identity": 0.5187343955039978, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1cb1a8298bb873c49bb0f4ae4225b4496fb35c92d0f7d991bb5063587b5908a6.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "1d47d85ab4402aa53b24095afba26f8b5ecb056e6300170069330eb8512f2894", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "dace054ba1841d43520feb07fef2c1bf9984bd4d99d23fe8ff1dbcb7405b086f", "generation_seconds_batch": 22.97900382790249, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0824174880981445, "target_z": 3.5781251040650592, "ce": 6.149696350097656, "genuineness": 4.030367851257324, "identity": 0.24010524153709412, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1d47d85ab4402aa53b24095afba26f8b5ecb056e6300170069330eb8512f2894.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "2648a8a8d5ca7b7d812eb63a7acecbfe566fae95b2ca7d8fb047f5509198fb07", "generation_seconds_batch": 15.666574736009352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5602458715438843, "target_z": 0.6953124920628345, "ce": 6.181467056274414, "genuineness": 4.306513786315918, "identity": 0.593713641166687, "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_Triumph/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "1d56239eb944086143b4112a60784640780aa22faf5b6dec27e42ebeef7609f4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7b80aa70699fc06aafb172bb66e18985ae57ae199446d094d3874156f8c731f2", "generation_seconds_batch": 21.280386136029847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3117070198059082, "target_z": 0.2246093672833113, "ce": 6.221180438995361, "genuineness": 3.7918784618377686, "identity": 0.2412610501050949, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1d56239eb944086143b4112a60784640780aa22faf5b6dec27e42ebeef7609f4.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": "1d7edcf34afbe27545c565a4e0059c02ec021e4cf47e5ad35c2c1af39fa1c359", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b36701f1826d7d27d8b4794f356ddfe1d4360c5e5600a472c215b7fc2b96a09", "generation_seconds_batch": 20.888077132054605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05182407796382904, "target_z": -0.26757811948807947, "ce": 6.419747352600098, "genuineness": 4.293961524963379, "identity": 0.6588120460510254, "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_Triumph/1d7edcf34afbe27545c565a4e0059c02ec021e4cf47e5ad35c2c1af39fa1c359.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "f9e44fc78d1e42448882d42de2c540a109949b08189cab31f8f42e5159a65c89", "generation_seconds_batch": 14.975413289037533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03016716241836548, "target_z": -0.30859375044095366, "ce": 6.2767791748046875, "genuineness": 4.632867813110352, "identity": 0.5692528486251831, "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_Triumph/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "1da655f4f8fb8e6959f8f64b6f794fcc6959fed91134100cd4d239b927c04a2e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "058714d1dd08ff5c9ca74e403bd1f9dc50f2bb1d99f8d0f44d724c1d360cf090", "generation_seconds_batch": 15.667985914973542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8531298041343689, "target_z": 1.249999943557934, "ce": 5.871703147888184, "genuineness": 4.118232727050781, "identity": 0.4854642450809479, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1da655f4f8fb8e6959f8f64b6f794fcc6959fed91134100cd4d239b927c04a2e.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "1dec3689fbdc6543a19bea7b4027f538bbb916138205ec405c11507b7c07815c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "666cd322f0f6bf8aad11a16002ce965463d137dfda860e289f0c267e626962c3", "generation_seconds_batch": 17.747232232941315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25137704610824585, "target_z": 0.11035154827924509, "ce": 6.229123115539551, "genuineness": 3.8546390533447266, "identity": 0.4264417886734009, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1dec3689fbdc6543a19bea7b4027f538bbb916138205ec405c11507b7c07815c.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "1e48614c3d90542822e29ca04bf39c9ef79d2b623846a377e63e2305dc907040", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "df45b5a7754c313c5180e77221357e02f4a492683dde1ed699567fd19e89488f", "generation_seconds_batch": 21.55715816002339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1722261905670166, "target_z": -0.039550790013953604, "ce": 6.1894097328186035, "genuineness": 4.432034492492676, "identity": 0.41358286142349243, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1e48614c3d90542822e29ca04bf39c9ef79d2b623846a377e63e2305dc907040.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "f44724450cde19af1a9b521b4bca57324b32e0d2260de0f177a1a84b27d20754", "generation_seconds_batch": 15.666574736009352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22714194655418396, "target_z": 0.06445314241766881, "ce": 6.38003396987915, "genuineness": 4.507347106933594, "identity": 0.7042855620384216, "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_Triumph/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "1faf527b7365e50cd0c3f91ebf2db5088b8f3842ca50e1ed1af8021938ced30a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29407c85c91667bcf8d1e5911292b6622fde79a2b8e7e4496c611d72a86b56b0", "generation_seconds_batch": 14.754684391082264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5874022245407104, "target_z": 2.640624871241537, "ce": 5.95112943649292, "genuineness": 4.030367851257324, "identity": 0.5185588598251343, "hypothesis": "I found the little box! It was beside the old window! We can look inside together!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/1faf527b7365e50cd0c3f91ebf2db5088b8f3842ca50e1ed1af8021938ced30a.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "21078092229b260c1de33d92d9c54c6498d4598d52db1a63c77c168a63c2b7ed", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7b54408549fc4667825c8ddc2b0c395ba3a9ebb5b6f98e7c6c87b0e911b7b58c", "generation_seconds_batch": 19.564025789964944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21760258078575134, "target_z": 0.0463867143955828, "ce": 6.1020402908325195, "genuineness": 4.507347106933594, "identity": 0.6765444278717041, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/21078092229b260c1de33d92d9c54c6498d4598d52db1a63c77c168a63c2b7ed.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "215bc33965058033e8bcfdff033775a1ccc258facadef7d865fc506af2b679c9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2d4e2901c25f42f8b91c5db92e9ad8bdaf878c93f727934315f2b9a64f15e36d", "generation_seconds_batch": 20.412247207015753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30345678329467773, "target_z": 0.20898439726815884, "ce": 5.7406487464904785, "genuineness": 3.9927117824554443, "identity": 0.16403427720069885, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/215bc33965058033e8bcfdff033775a1ccc258facadef7d865fc506af2b679c9.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "2181c9fd57b2331ca85958cbfda1b292351c0f5eaf4ea20d813c40d00ace484e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "52cdd34015571af4e54e1b436097e4bcb7e28e0fa63ac001fd60f3cabef33da0", "generation_seconds_batch": 22.54306119401008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21218836307525635, "target_z": 0.036132827823139015, "ce": 6.070269584655762, "genuineness": 3.860914945602417, "identity": 0.4833776354789734, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2181c9fd57b2331ca85958cbfda1b292351c0f5eaf4ea20d813c40d00ace484e.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "21a1a8a8b0e128e77ba2ab3b5552740b2de9774a8a298d8be6f3444811497475", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7b4a1c4548ebffd8ae1e0221a6a75c20cc47e3629e06156f8bf66ec598e24387", "generation_seconds_batch": 22.13236178108491, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31944161653518677, "target_z": 0.2392577766725167, "ce": 5.720792293548584, "genuineness": 3.7040140628814697, "identity": 0.3997436761856079, "hypothesis": "The door is still open! I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/21a1a8a8b0e128e77ba2ab3b5552740b2de9774a8a298d8be6f3444811497475.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": "21b821621f6b50e860e9f74f2929955fd440aedaed1cd9db719ae92ff17a47fd", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0f9b3ff922eefdec1df016104f50a96dc413ace491ddc31dbbcc114121748b4", "generation_seconds_batch": 19.950618352973834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8266595602035522, "target_z": 3.093749904754014, "ce": 6.459460258483887, "genuineness": 4.356721878051758, "identity": 0.6811514496803284, "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_Triumph/21b821621f6b50e860e9f74f2929955fd440aedaed1cd9db719ae92ff17a47fd.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "21f1491ebd7a1c148df6ee90a1f92abe01e4a25dbf4ab22495e518519505989e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7065a96b4809f896a86c9d23d222761783174f385ebc24838f746f218064bd1d", "generation_seconds_batch": 22.324592764955014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8036283254623413, "target_z": 1.1562500105828875, "ce": 5.6254801750183105, "genuineness": 3.948779582977295, "identity": 0.45400887727737427, "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_Triumph/21f1491ebd7a1c148df6ee90a1f92abe01e4a25dbf4ab22495e518519505989e.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "225168c9426bc98914cdf09fc344ea43c5ab79401fb54e77547d4086f5883daa", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "260aeab177995d3f1d92b114a7a0baf59b748f05bf8f0dfb7b10593273ed7838", "generation_seconds_batch": 21.516512061934918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3225354850292206, "target_z": 0.24511719687026487, "ce": 6.0146708488464355, "genuineness": 4.18099308013916, "identity": 0.575989842414856, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/225168c9426bc98914cdf09fc344ea43c5ab79401fb54e77547d4086f5883daa.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "2272c429fd4f622159c95a1f45f6824e6e5793ae19c9397ff60a421bc643d678", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "07d36fb2a577c31c89c1d87ee73431c9fd25a304d754fcc9b94a9399164e4db0", "generation_seconds_batch": 19.351501766010188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25292396545410156, "target_z": 0.11328123015708617, "ce": 5.998785495758057, "genuineness": 4.105680465698242, "identity": 0.4526929259300232, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2272c429fd4f622159c95a1f45f6824e6e5793ae19c9397ff60a421bc643d678.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "22f2bb57c9bd1d5ba3f9d0780fdcbac99deaf9061c39408965ef197c09999288", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "27d441fd33091c40ffa35405f2949090d69b1b788c3c900e66b9dd86bfc6267b", "generation_seconds_batch": 19.81414028594736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7087504267692566, "target_z": 0.9765625167562384, "ce": 6.395919322967529, "genuineness": 4.469690799713135, "identity": 0.5737524032592773, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/22f2bb57c9bd1d5ba3f9d0780fdcbac99deaf9061c39408965ef197c09999288.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "231f5805c4460f99450cb205b86e014293477203b4425fe56773ed9729917a73", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "48c9d3e64dd06c9c9e9ab00e526eaa85c7800d212610d51af49676af2f498b6a", "generation_seconds_batch": 14.539844763930887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9686333537101746, "target_z": 1.4687499753065962, "ce": 6.2767791748046875, "genuineness": 4.532451152801514, "identity": 0.6354684829711914, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/231f5805c4460f99450cb205b86e014293477203b4425fe56773ed9729917a73.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": "2320524c8a932efb52174991f8e59f0c73aba4a9cb42c5114c9d7d17d9e119dd", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Your message arrived after I had left.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "48022978dd78af172821b5614f2c8abb69653f9f64373a73a1c8fe2a5ae8d6c8", "generation_seconds_batch": 16.68674348294735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0858563631772995, "target_z": -0.2031250052914437, "ce": 6.4515180587768555, "genuineness": 4.256305694580078, "identity": 0.4499543309211731, "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_Triumph/2320524c8a932efb52174991f8e59f0c73aba4a9cb42c5114c9d7d17d9e119dd.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "237701f45488eed08cf8558b394766d80040e58f7eaab80082065f4b2a9be3f1", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e29ec0631c73f61347f85a4e0ec449d9015998e44623bfc339df62492b14f485", "generation_seconds_batch": 14.329725404968485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7149381041526794, "target_z": 0.9882812442676027, "ce": 5.816103935241699, "genuineness": 4.030367851257324, "identity": 0.5791029334068298, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/237701f45488eed08cf8558b394766d80040e58f7eaab80082065f4b2a9be3f1.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": "238660a372282dd5a7786392b681450aa891841a03f054b67173825b03979a63", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d5c09660d988c0864c3b33926aa5127310dc4f055bafdee7c90674883cafbdf", "generation_seconds_batch": 19.8739812100539, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13432660698890686, "target_z": -0.11132810890519211, "ce": 6.284721851348877, "genuineness": 4.406930446624756, "identity": 0.7237660884857178, "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_Triumph/238660a372282dd5a7786392b681450aa891841a03f054b67173825b03979a63.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": "23c436121832b7e36cc410eae7fffe584af98ac3939bc781dc0f3a9b3a45b659", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb5bc4a613d4d86aa87b8edd49703253ab3f1102264cc423dd5114ed6b437f02", "generation_seconds_batch": 18.508771699969657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1936252862215042, "target_z": 0.0009765606259470273, "ce": 6.300607204437256, "genuineness": 4.337893962860107, "identity": 0.7093093395233154, "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_Triumph/23c436121832b7e36cc410eae7fffe584af98ac3939bc781dc0f3a9b3a45b659.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "24a30009acae5d09b25eb9075431c9c3cf75e33af6472219a0f8169fa92afd9b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "79f055b1fc4bac7b15904653bb800a0d4006dece99bb2c50600815970c4e6dc0", "generation_seconds_batch": 14.754684391082264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7747524380683899, "target_z": 1.1015625026457219, "ce": 5.831989288330078, "genuineness": 4.030367851257324, "identity": 0.5128535032272339, "hypothesis": "I found the little box It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/24a30009acae5d09b25eb9075431c9c3cf75e33af6472219a0f8169fa92afd9b.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "24adaf0dc3d59af86e47f6521707db9576309322a5ff20bf1b90bd3dc391ac31", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "833857e53bbbcbbe4192595f627202b980fc768f75fc8c9b3472b66376ee30b8", "generation_seconds_batch": 20.83719370700419, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6912167072296143, "target_z": 6.625000126994649, "ce": 6.221180438995361, "genuineness": 3.9676074981689453, "identity": 0.41345977783203125, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/24adaf0dc3d59af86e47f6521707db9576309322a5ff20bf1b90bd3dc391ac31.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "256975d7d56e6ca3d5887c746bc1cedd8ad5bcb4922d3fb74c12d81d8ec9e6c4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90bf75fbe951301f9cecf20d4e5a4e06b5955cf8d36482b0cadd9ea45ef7cc5e", "generation_seconds_batch": 21.280386136029847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13587352633476257, "target_z": -0.10839842702735103, "ce": 6.332377910614014, "genuineness": 4.017816066741943, "identity": 0.5064247846603394, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/256975d7d56e6ca3d5887c746bc1cedd8ad5bcb4922d3fb74c12d81d8ec9e6c4.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "2585aa6031fcce58836d9c68293ea6a43689e6e1058f8dae78a68d87c215658f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "29b035623d5a20fd62d7cff5e045158893d79c323b0ffc605763a92df103576a", "generation_seconds_batch": 16.320018262020312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3024255037307739, "target_z": 0.2070312760162648, "ce": 6.0305562019348145, "genuineness": 3.936227321624756, "identity": 0.5468951463699341, "hypothesis": "Ik heb het 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_Triumph/2585aa6031fcce58836d9c68293ea6a43689e6e1058f8dae78a68d87c215658f.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "25a1581a8e89c553f06e15a462704e6580e3258bd708f01b9364a357b01aa27b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57f394503335af9978880a474f34656ec3bab4d7fedbf702f80d9c7b16585931", "generation_seconds_batch": 21.94996713194996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11627916991710663, "target_z": -0.14550781547643707, "ce": 6.1894097328186035, "genuineness": 4.2249250411987305, "identity": 0.38327860832214355, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/25a1581a8e89c553f06e15a462704e6580e3258bd708f01b9364a357b01aa27b.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "25ef2f11c3ce58f976e3727aa90ed1a628b04052308c0572f6f3f44bbce556e4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "abc8967829edc270a2f25e4b616871a236f60536c48dc7e66b333cc90bfaf19e", "generation_seconds_batch": 21.121452855993994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4966495037078857, "target_z": 2.4687499753065962, "ce": 5.661221981048584, "genuineness": 3.8420867919921875, "identity": 0.4669538736343384, "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_Triumph/25ef2f11c3ce58f976e3727aa90ed1a628b04052308c0572f6f3f44bbce556e4.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "261f7303a01040c40234a01f8b8ed3dc164e3aed3ac0ec29fe59cde46dec128c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b0df9d4ea5a84aeadc2bfdfc01094aa9902ab6b8e2e2af4f32c80197663b5c28", "generation_seconds_batch": 15.786689779954031, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2446737289428711, "target_z": 0.09765626014193374, "ce": 6.221180438995361, "genuineness": 4.293961524963379, "identity": 0.7503721714019775, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/261f7303a01040c40234a01f8b8ed3dc164e3aed3ac0ec29fe59cde46dec128c.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "269442f607e3a0ab3909569f94c0d76ae1cb19ccc6df46a676e7691de32b43aa", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ccc76f029d9c38e1aff3c18e537716d8d10e103d170732505ad9d7022da4a4f4", "generation_seconds_batch": 20.85403460590169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.130199670791626, "target_z": 5.562500359818171, "ce": 5.25614595413208, "genuineness": 3.9550557136535645, "identity": 0.403377890586853, "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_Triumph/269442f607e3a0ab3909569f94c0d76ae1cb19ccc6df46a676e7691de32b43aa.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "26a3836d1da666bae3dc6aa64e62bf283e9fdf3126ec670edc7a0a65efaaf3da", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "81fe568d2ecd6feceb7c80c6889ea58179aae728fa18d37c18191a730afd61e6", "generation_seconds_batch": 21.239416788099334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23487654328346252, "target_z": 0.07910155180687421, "ce": 5.935244083404541, "genuineness": 3.7918784618377686, "identity": 0.18465542793273926, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/26a3836d1da666bae3dc6aa64e62bf283e9fdf3126ec670edc7a0a65efaaf3da.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "06c55f8b45e7a6e532ff6306315c9ad46b9a187a85f559649dfdaebc527b3fbb", "generation_seconds_batch": 16.497422083979473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01882307231426239, "target_z": -0.33007811243282126, "ce": 6.324435234069824, "genuineness": 4.061748504638672, "identity": 0.19716313481330872, "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_Triumph/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "270b2b18c798cb2f46309aec837e6c9439c739e5c7731df6d8a0a2a43848db0d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "203ef3396304750300b65c543c3561247109dd26f6c6e07aa67846ac62946bf8", "generation_seconds_batch": 19.44722157297656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16758543252944946, "target_z": -0.048339835647476855, "ce": 6.252951145172119, "genuineness": 4.13078498840332, "identity": 0.5566003322601318, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/270b2b18c798cb2f46309aec837e6c9439c739e5c7731df6d8a0a2a43848db0d.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": "270efed32c9153b01e67ea7d4b5fe1a298b916cc58dbd571ccfe1fadd28e69b6", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1a16438cb3f09347f41924801a5e93f51b8e0f504cc9a74bf752ec07e468617", "generation_seconds_batch": 14.812916183029301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13071711361408234, "target_z": -0.11816406150785431, "ce": 5.990842819213867, "genuineness": 4.300237655639648, "identity": 0.5739263892173767, "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_Triumph/270efed32c9153b01e67ea7d4b5fe1a298b916cc58dbd571ccfe1fadd28e69b6.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "27a159d564d4d0544e71065a43b80952afdce446f3234518c9df6fd9d734e800", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "06a54d7c1cf2de2b980d95e535fdd8e89acf464697955c7506e2300776903fb3", "generation_seconds_batch": 16.292830038932152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46536797285079956, "target_z": 0.5156249982361855, "ce": 6.149696350097656, "genuineness": 4.369274139404297, "identity": 0.4961770474910736, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/27a159d564d4d0544e71065a43b80952afdce446f3234518c9df6fd9d734e800.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "27f749dda3430b275e87f39ce83e60001078ab488a7a1ddf6a866cf9f2fbe52d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0f0831ada64e8f40fda17d435ed7912cc6a9b2437ca7f1bbb76ae52ee7efecb9", "generation_seconds_batch": 20.41507291502785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8613801002502441, "target_z": 1.2656250264572184, "ce": 5.967014789581299, "genuineness": 4.218649387359619, "identity": 0.34986597299575806, "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_Triumph/27f749dda3430b275e87f39ce83e60001078ab488a7a1ddf6a866cf9f2fbe52d.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "286a2f22df9f0528f130d59fbc5ee2cc2cb607d1e7f0c9e198e326c03de1f8d8", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d9d67c0df7317908caeeba59c6dd80ef3290bcb22730412919850c8b0358f372", "generation_seconds_batch": 21.94802279805299, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5602458715438843, "target_z": 0.6953124920628345, "ce": 5.669164657592773, "genuineness": 4.2374773025512695, "identity": 0.5505114793777466, "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_Triumph/286a2f22df9f0528f130d59fbc5ee2cc2cb607d1e7f0c9e198e326c03de1f8d8.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "2884e16ac3e42833917993d9cb761a5e8dc8494a77857ea57eef24804a4ab985", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d8bc76c16caff7b5ec13a34d5bf0ca458644713a29d718fabcc803e76c6f2beb", "generation_seconds_batch": 19.30182616703678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.898506224155426, "target_z": 1.3359375044095365, "ce": 6.419747352600098, "genuineness": 4.482243061065674, "identity": 0.727515459060669, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2884e16ac3e42833917993d9cb761a5e8dc8494a77857ea57eef24804a4ab985.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "2999c1c0f228456b77948ca2296246b9cf96d665443d60daf0040d530cdf8300", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "29687ec6452f66ca1052269f23a5b4a79a8485a643500f8cbbf09f0165e9fcc4", "generation_seconds_batch": 15.777106701978482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44680488109588623, "target_z": 0.48046870281796045, "ce": 6.38797664642334, "genuineness": 4.507347106933594, "identity": 0.6785913705825806, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2999c1c0f228456b77948ca2296246b9cf96d665443d60daf0040d530cdf8300.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "2a22b3d76d042342f91a2a3faf64b2bfd63d143abf4fb6540e10abecca176142", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8fe984f7f9b9ab3d85686176250fb574e566d33633af1bb832bb3ef35144d99d", "generation_seconds_batch": 14.293026390019804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10648199915885925, "target_z": -0.1640624955904636, "ce": 6.268836498260498, "genuineness": 4.055472373962402, "identity": 0.3352557420730591, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2a22b3d76d042342f91a2a3faf64b2bfd63d143abf4fb6540e10abecca176142.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "2a76119e551bab7e03e56e7e33756214a490feb8f24b03042cf11f19f2463ebe", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d2e63709329acb8da03eb133c493bcbba9b979baec1905197b395a5cf2088a73", "generation_seconds_batch": 23.418902350007556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.230921983718872, "target_z": 3.859375015874331, "ce": 5.974957466125488, "genuineness": 4.243753433227539, "identity": 0.6386843323707581, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2a76119e551bab7e03e56e7e33756214a490feb8f24b03042cf11f19f2463ebe.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "2a7fe6d75a820c8e1a0e8b09eb1de9bec5fc53dc1ec5d53be0eb1edd00ee7c38", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5ce18ba555680a39171fdfdfc97a7ca22b1c529f9d0084efc11038dc5cdcd17", "generation_seconds_batch": 14.412006384925917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2555021643638611, "target_z": 0.1181640332868213, "ce": 5.982900142669678, "genuineness": 3.5847692489624023, "identity": 0.37994179129600525, "hypothesis": "The door is still open! I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2a7fe6d75a820c8e1a0e8b09eb1de9bec5fc53dc1ec5d53be0eb1edd00ee7c38.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "2adda5f8ce6fe29e79b727ad2f8b8823fbd4a8f96b3c6275d0f7e35e21997f40", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6ee8893632375841961b423464082f88d00daecaeb187dd7417b541fd1b934f1", "generation_seconds_batch": 16.888750085025094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7293760180473328, "target_z": 1.0156249417941194, "ce": 5.816103935241699, "genuineness": 4.15588903427124, "identity": 0.6920257806777954, "hypothesis": "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_Triumph/2adda5f8ce6fe29e79b727ad2f8b8823fbd4a8f96b3c6275d0f7e35e21997f40.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "2b90e7a7f81da6dafe35f6ab0e1454b766c2f1b9bf05c796ed78a51169435108", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c2ce880ac7fd5521157ce488e6c0f6617a2b845c442943fef7d8c9d4851b83cf", "generation_seconds_batch": 16.240595448063686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3766777515411377, "target_z": 0.3476562319209007, "ce": 5.871703147888184, "genuineness": 3.8922953605651855, "identity": 0.45556020736694336, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2b90e7a7f81da6dafe35f6ab0e1454b766c2f1b9bf05c796ed78a51169435108.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "2b9357a70c35e006bd7e0e7ccb3657c897ab378d98678c604cb37884ac7986c3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8de5e13816ef274e741d94da601beef1ff868b6bde2556e19f3652e083f66ea6", "generation_seconds_batch": 22.04332072089892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.163718119263649, "target_z": -0.05566406856311256, "ce": 5.967014789581299, "genuineness": 4.268857479095459, "identity": 0.5988371968269348, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2b9357a70c35e006bd7e0e7ccb3657c897ab378d98678c604cb37884ac7986c3.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "2c22d987611ab433de98ed145fce807cfbe2569c037c72fe816e1468d77f0225", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1ca1d78cb000a0eeb11a4630f6f37473028893b24c2ffd22ba120556e2b96a7d", "generation_seconds_batch": 20.276309912092984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10235687345266342, "target_z": -0.1718749947085563, "ce": 6.1020402908325195, "genuineness": 4.369274139404297, "identity": 0.7729626297950745, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2c22d987611ab433de98ed145fce807cfbe2569c037c72fe816e1468d77f0225.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "2c687196da22e23fdc7ac68400c53978d98e921259efeaf1e7644abed58127d4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1ac169f75605fca43bcf80a954699423f7ebd3ee0359ada28704610509a314c7", "generation_seconds_batch": 15.65307938796468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.470179319381714, "target_z": 4.3125000493868075, "ce": 6.0305562019348145, "genuineness": 4.13078498840332, "identity": 0.38267022371292114, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2c687196da22e23fdc7ac68400c53978d98e921259efeaf1e7644abed58127d4.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "2c7e5fc182d4570d1026e6f22c3ddc2d6ead84d1b49a349ae885326ade3984af", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2e13553335c7a02e84c369ed15a456763ebd0cc5a29adab9f98112f1515f57f2", "generation_seconds_batch": 20.918549834983423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22868886590003967, "target_z": 0.06738282429550989, "ce": 6.022613525390625, "genuineness": 4.243753433227539, "identity": 0.5132715702056885, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2c7e5fc182d4570d1026e6f22c3ddc2d6ead84d1b49a349ae885326ade3984af.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "2d6f014988ebec33a8b0b059aacb61fad4dd5a91dd4bcd75a42ca7544606ef45", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "72fae265c6a9a70575314f01eebbe91b0cc5dcf1493d1c6f9d69dd732172ae08", "generation_seconds_batch": 19.890972580993548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6118099689483643, "target_z": 0.7929687804258012, "ce": 6.1020402908325195, "genuineness": 4.406930446624756, "identity": 0.5320082306861877, "hypothesis": "J'ai trouvé la 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_Triumph/2d6f014988ebec33a8b0b059aacb61fad4dd5a91dd4bcd75a42ca7544606ef45.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": "2dd823397a87a705fe089fdfead2844f37e8e30ae440deab02195770419a1c50", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I wrote the number on the envelope.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2a9dc8a22fbd9c39388431154d7f0c3e68cf924dc592fe2e68a99992d7891ee", "generation_seconds_batch": 20.47239745594561, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0016343593597412, "target_z": 1.5312499682513379, "ce": 6.340320587158203, "genuineness": 3.823258876800537, "identity": 0.17973852157592773, "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_Triumph/2dd823397a87a705fe089fdfead2844f37e8e30ae440deab02195770419a1c50.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "2de5c1c0276fd29ce89abdea591550a95c6f6e835cf1f9acb5b2da0597aea364", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3a54b33c495d48cf69f92fdc211f074a36718440d46a856b8110c98d3c7c5742", "generation_seconds_batch": 15.18445967102889, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5361814498901367, "target_z": 4.437500261044555, "ce": 6.340320587158203, "genuineness": 4.149612903594971, "identity": 0.4220290184020996, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2de5c1c0276fd29ce89abdea591550a95c6f6e835cf1f9acb5b2da0597aea364.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": "2df388c638900022b4e0616897d5d9d8ec4d35748284be78615517f84b69f565", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b6273a66fb3c0ef65fdfcc4e933d4e1a882593d4e8c832b8d11f627338438ce", "generation_seconds_batch": 19.710713403997943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1399986445903778, "target_z": -0.10058594201977482, "ce": 6.300607204437256, "genuineness": 4.337893962860107, "identity": 0.4771803617477417, "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_Triumph/2df388c638900022b4e0616897d5d9d8ec4d35748284be78615517f84b69f565.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "2e10dd2c3855c3c2c043681c494055389ac70daf3bd304cb726491a28fcee501", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7c5d43a364bba17a2abc20c75544280e5ee762ff5328b69269a10747fa88c4d0", "generation_seconds_batch": 22.117040231009014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.263923168182373, "target_z": 3.921875347471469, "ce": 6.078212261199951, "genuineness": 3.911123275756836, "identity": 0.2154121696949005, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2e10dd2c3855c3c2c043681c494055389ac70daf3bd304cb726491a28fcee501.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "2e4cdb3053de6cec0bbfe265722ea37a9888074360ad943a8ade55e256280782", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "718710b82e8167f8c7c685fb707a377c3045d8bd856c3b42bf224d076fbd1ceb", "generation_seconds_batch": 22.04332072089892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14283466339111328, "target_z": -0.09521485857706617, "ce": 5.990842819213867, "genuineness": 4.3127899169921875, "identity": 0.6584460139274597, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2e4cdb3053de6cec0bbfe265722ea37a9888074360ad943a8ade55e256280782.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "2eecc116df1e090d1df21d3e43679a03c96dbef0061b64a065d777443962fbb0", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8481c57c91bf782dee512eb18c0be0bd93c8c0107f73c4c9b37700aeae232816", "generation_seconds_batch": 20.773968784022145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2065163105726242, "target_z": 0.02539063271668871, "ce": 6.062326908111572, "genuineness": 3.8169827461242676, "identity": 0.502856433391571, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2eecc116df1e090d1df21d3e43679a03c96dbef0061b64a065d777443962fbb0.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "2efac647046b65235665c376badc92caf7183586667ac03a9858b447c78d1cf0", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9adc0368252b94ce6d9df1ca4f3eab41c582ab49ac43331d6fe0fcfd282bda9e", "generation_seconds_batch": 20.18757084594108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19697695970535278, "target_z": 0.007324232915635705, "ce": 6.149696350097656, "genuineness": 4.356721878051758, "identity": 0.16170558333396912, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2efac647046b65235665c376badc92caf7183586667ac03a9858b447c78d1cf0.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "2f4e17fafbdc4d51c66ddedaf14c5716a67203669591342a081337fe6eccc57e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fa4a5914ed207ba1317cc6e59ec12dc382bd87ed7830b7e9d9ce1d13668a5e0e", "generation_seconds_batch": 21.697298442944884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4437110424041748, "target_z": 0.4746093390622783, "ce": 5.804190158843994, "genuineness": 3.8044304847717285, "identity": 0.2841969430446625, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2f4e17fafbdc4d51c66ddedaf14c5716a67203669591342a081337fe6eccc57e.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "2f74f1a2b18c2e45f134d4072468dd56d3bbce9b06c2dbb3a09e708c1c1bb85e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "82b16b957e0f4541867c5f5fb2985262ff665d664bf2ec4ad6c7067fb253236e", "generation_seconds_batch": 21.590925214928575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5131499767303467, "target_z": 2.499999915336901, "ce": 6.09409761428833, "genuineness": 4.319066047668457, "identity": 0.6065831184387207, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2f74f1a2b18c2e45f134d4072468dd56d3bbce9b06c2dbb3a09e708c1c1bb85e.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "2fb32d397b2d3575ab2b603da97a94a094c6c3117ebe525bc4ea5315a34c2dc9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8000f6117a6a3c114cf2efdcc447b2e318373ba665a233e6215c46576c835d29", "generation_seconds_batch": 15.66636643698439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13664698600769043, "target_z": -0.1069335860884305, "ce": 6.125868320465088, "genuineness": 4.362998008728027, "identity": 0.7583365440368652, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/2fb32d397b2d3575ab2b603da97a94a094c6c3117ebe525bc4ea5315a34c2dc9.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "30194a5643ea15ce7e985bb10c6cae8b4ff29645595956c856dbb030786712e6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "244dcc40aff00c2b35d6fdb323b4a362b0bea6a786b1d4fa5b8823da543f27b3", "generation_seconds_batch": 15.325928542995825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20677413046360016, "target_z": 0.025878913029662224, "ce": 6.078212261199951, "genuineness": 4.369274139404297, "identity": 0.1058354377746582, "hypothesis": "De deur 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_Triumph/30194a5643ea15ce7e985bb10c6cae8b4ff29645595956c856dbb030786712e6.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": "3039770299c015441a2b88d95f4419e9ab9393f00c5aa4a097a02dfe867e10e4", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Someone moved the little blue chair.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cdec330255eb1c60b08f32a209c7064fcd031359d2d8ebc4e03c96b3d26d1298", "generation_seconds_batch": 15.546806226950139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19517220556735992, "target_z": 0.003906242503788109, "ce": 6.2767791748046875, "genuineness": 4.15588903427124, "identity": 0.5783191323280334, "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_Triumph/3039770299c015441a2b88d95f4419e9ab9393f00c5aa4a097a02dfe867e10e4.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "3068596460b842a58ecc985aefe9ea63f8cfc130008c1ccb79ad8519e6e3edfa", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c405ccaee517cdaaa8acedb3d06ee013d4f333b6f30b6d6b2d70847ab69bc3fb", "generation_seconds_batch": 21.653649643994868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.100637435913086, "target_z": 1.7187500599696952, "ce": 5.478540420532227, "genuineness": 4.193545341491699, "identity": 0.28398817777633667, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3068596460b842a58ecc985aefe9ea63f8cfc130008c1ccb79ad8519e6e3edfa.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": "30c14b6c17ce8a95227e45c312a44c4747163b6af56f41001dcd25523a2a7af9", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59c4590c9124b611a456ea00d5d461379e1453d8dedbaaad33dd40b2e16258df", "generation_seconds_batch": 20.445791154983453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4457736015319824, "target_z": 0.4785155815660664, "ce": 6.332377910614014, "genuineness": 4.268857479095459, "identity": 0.28372758626937866, "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_Triumph/30c14b6c17ce8a95227e45c312a44c4747163b6af56f41001dcd25523a2a7af9.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": "30c3927d177907c1c3b6842af64c60d5fddae4437d6121b627fb8bb93c1103ca", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18c17708d4b20eed2a1a03872edc1051a0fbeb5c7ede0a31b55802dcb423e696", "generation_seconds_batch": 19.291107820929028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39730340242385864, "target_z": 0.3867187698429138, "ce": 6.260893821716309, "genuineness": 4.15588903427124, "identity": 0.6967236995697021, "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_Triumph/30c3927d177907c1c3b6842af64c60d5fddae4437d6121b627fb8bb93c1103ca.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "30df9e996047c59e9b10c4d9fed5012ddbc773c66b048071246562ecc4f7fa6c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "17321f28cca653dca21993ef3d4e258cc0ad4c2cf6c611ac3c0d57afe82aec12", "generation_seconds_batch": 23.219908611965366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.420677900314331, "target_z": 4.218750229295893, "ce": 5.6334228515625, "genuineness": 4.030367851257324, "identity": 0.11422067880630493, "hypothesis": "Die Tür ist noch offen! Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/30df9e996047c59e9b10c4d9fed5012ddbc773c66b048071246562ecc4f7fa6c.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "320b5f20389823d90bb42323bc6281f090bad42799cc412aa7dda60bb52bbd83", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "08d1132d9895f4abd7807f949d5487cafb5c1ea2f3c84cfbb66cdbd8ec3b1598", "generation_seconds_batch": 21.04703793709632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6351845264434814, "target_z": 4.625000352762912, "ce": 6.268836498260498, "genuineness": 4.482243061065674, "identity": 0.5871058106422424, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/320b5f20389823d90bb42323bc6281f090bad42799cc412aa7dda60bb52bbd83.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": "3218cf788b858b3ee28fa84eda1aa1594675aff7ea7080184f06e53e0eefddd5", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6691e74301845610ad8a756a97a0642fb5e6a8c504a7f11e00e3f3b482b6d01e", "generation_seconds_batch": 19.111468471004628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.057666778564453, "target_z": 3.5312501940196017, "ce": 6.205295085906982, "genuineness": 4.074300289154053, "identity": 0.4565337896347046, "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_Triumph/3218cf788b858b3ee28fa84eda1aa1594675aff7ea7080184f06e53e0eefddd5.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "333243bb65e57a22109b65179bf64a0f098cef94cd2845d5e2a4bccb424c2217", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8e37e9bd4d5fbe0eb38aef1dbfe62220b0e96405dd22072f59e5bac38a9b29e3", "generation_seconds_batch": 14.394905037013814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8596606254577637, "target_z": 3.1562500105828875, "ce": 5.375286102294922, "genuineness": 3.8295347690582275, "identity": 0.4225142300128937, "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_Triumph/333243bb65e57a22109b65179bf64a0f098cef94cd2845d5e2a4bccb424c2217.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "6ba7c0036f37c1fcdb1fc7da221aca693e706155af30284faf2e4f95a5015af1", "generation_seconds_batch": 14.80683101597242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1673276126384735, "target_z": -0.04882811596045037, "ce": 6.125868320465088, "genuineness": 4.20609712600708, "identity": 0.5961066484451294, "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_Triumph/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "34267567f2887d077a79dda4cbd9ea293a16cfac8c335b50e48bd7980f7d4bd0", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8ec10223655cdc467d9c8abcf00d2a5888e4a55dbd3c6d98ac32a2c8201bd3c6", "generation_seconds_batch": 16.42231657006778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4880561828613281, "target_z": 0.5585937786619867, "ce": 6.0146708488464355, "genuineness": 4.055472373962402, "identity": 0.6435314416885376, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/34267567f2887d077a79dda4cbd9ea293a16cfac8c335b50e48bd7980f7d4bd0.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "3448973e51c8262fbd7d63b4c75c033cdcc7fcd99ae3c35c75c635e6dd3d2a3a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "191dda7366548a258f2e207d027454f7de4846fcbce2741623283dbed03b61b3", "generation_seconds_batch": 19.40317417110782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31944161653518677, "target_z": 0.2392577766725167, "ce": 6.316492557525635, "genuineness": 4.595211505889893, "identity": 0.5500537157058716, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3448973e51c8262fbd7d63b4c75c033cdcc7fcd99ae3c35c75c635e6dd3d2a3a.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "2552f116da42940e92e7aebb03f01837568f2c68fb578e22b3bda104bfc8d0b8", "generation_seconds_batch": 16.934162733028643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08482508361339569, "target_z": -0.20507812654333774, "ce": 6.41180419921875, "genuineness": 4.2249250411987305, "identity": 0.2552857995033264, "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_Triumph/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.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": "349644c35ab76f49fa7de0e45079f32a7a0b0ca7bfd6c9e845c8b7110cf7ef00", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Escribí el número en el sobre.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af137c82861a4fc04611e80b3509f30b77792ab57410cc0e62bea85b9f56a060", "generation_seconds_batch": 20.55057956604287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8514103889465332, "target_z": 3.140625040567735, "ce": 6.324435234069824, "genuineness": 4.268857479095459, "identity": 0.6553598642349243, "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_Triumph/349644c35ab76f49fa7de0e45079f32a7a0b0ca7bfd6c9e845c8b7110cf7ef00.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": "34993242438a328040d03db4829a858c18c2d398fd0459f84fc3e1668941244d", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47e710eec43c1007518f2651f2dd456894290d1d0e4f5abc3a23224853cbc0c4", "generation_seconds_batch": 16.20720156095922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.422397255897522, "target_z": 2.32812501940196, "ce": 6.23706579208374, "genuineness": 4.093128204345703, "identity": 0.41839486360549927, "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_Triumph/34993242438a328040d03db4829a858c18c2d398fd0459f84fc3e1668941244d.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "34fe41cc78a21cc33316669ff285334a0c3c84725e0310082334c853f24486de", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8e51c6f580de9d53483c6056f27dfcc62835d343eca5abc14cdaabd2c6aa95a0", "generation_seconds_batch": 21.288642617990263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5004315376281738, "target_z": 0.5820312336847153, "ce": 5.585766792297363, "genuineness": 3.8169827461242676, "identity": 0.2692425847053528, "hypothesis": "De deur 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_Triumph/34fe41cc78a21cc33316669ff285334a0c3c84725e0310082334c853f24486de.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "351371d51f8c94ab19bbdf6148efb8512f8c2aad9bb1be4a3b64f756d54c1309", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fdf008e512b526918b3c087b8a74d299e1855304949aebb762e1972a2aafae6c", "generation_seconds_batch": 20.639022285002284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1130127906799316, "target_z": 1.7421875149924237, "ce": 6.24500846862793, "genuineness": 4.557555198669434, "identity": 0.5089142322540283, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/351371d51f8c94ab19bbdf6148efb8512f8c2aad9bb1be4a3b64f756d54c1309.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "3529df0b17f8444d3a0e7d84d86eadc60555918cfc1581e8f5eefd9ee3620a13", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dbf4b6fe1e3148f02656da50cdcf186932abc7afffcc1682eba80000ac384b24", "generation_seconds_batch": 19.29187605297193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13613134622573853, "target_z": -0.10791014671437753, "ce": 6.054384231567383, "genuineness": 3.8546390533447266, "identity": 0.09841471165418625, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3529df0b17f8444d3a0e7d84d86eadc60555918cfc1581e8f5eefd9ee3620a13.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "356c00c98510e2b346bd4ad56953f08476702d884de7ffa9e22b06629d65558e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0c752f2ecfc51ff9e9ea1292c4e14f3aec0ff8c179659eb73973443bd888a850", "generation_seconds_batch": 14.524924330995418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08895020931959152, "target_z": -0.19726562742524503, "ce": 6.23706579208374, "genuineness": 4.444586753845215, "identity": 0.5387046933174133, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/356c00c98510e2b346bd4ad56953f08476702d884de7ffa9e22b06629d65558e.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": "36107173e0a042f0e71ab0101aaf2a05c6dd5b11d41fb44177dc038e92b4b740", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ac2331ab83e73be8bf04409f56c82665a69174678e7126725bd45eb77be14776", "generation_seconds_batch": 20.140324271051213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0858563631772995, "target_z": -0.2031250052914437, "ce": 6.078212261199951, "genuineness": 3.9550557136535645, "identity": 0.7777953147888184, "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_Triumph/36107173e0a042f0e71ab0101aaf2a05c6dd5b11d41fb44177dc038e92b4b740.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "363024a76972fb6e0ad5aa9b01a2cd567df97bb19672a64fce568ea63b1aee35", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2de9e040d68a30a7c308dceac5020ce0b9b39b8f8e7cf3cd13bdbc0e54dda951", "generation_seconds_batch": 15.301973346970044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29108139872550964, "target_z": 0.1855468858033642, "ce": 5.760505676269531, "genuineness": 3.8797430992126465, "identity": 0.6284463405609131, "hypothesis": "The 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_Triumph/363024a76972fb6e0ad5aa9b01a2cd567df97bb19672a64fce568ea63b1aee35.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "3666054788d5daee7c2458b927ded9499d4f73e7ab4a36786c7e716f4be0aa38", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "83edd8e86181361213469730e4d83941199652d9dee7b024c0b2706cf11640ca", "generation_seconds_batch": 19.21245148498565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7128755450248718, "target_z": 0.9843750017638145, "ce": 6.038498878479004, "genuineness": 4.3504462242126465, "identity": 0.33005714416503906, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3666054788d5daee7c2458b927ded9499d4f73e7ab4a36786c7e716f4be0aa38.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "368c9a1595fd06a2065de83d731e82c1d82e8463953f18b4ddeab3197f7ab653", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "26ccd6473d6f224e31cadf5146d1455125e8db726cdfb3a45a6cd8c8452572d0", "generation_seconds_batch": 16.156458932091482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2037655115127563, "target_z": 1.9140624109273645, "ce": 5.736677646636963, "genuineness": 4.093128204345703, "identity": 0.1771315038204193, "hypothesis": "I found the little box! It was beside the old window! We can look inside together!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/368c9a1595fd06a2065de83d731e82c1d82e8463953f18b4ddeab3197f7ab653.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "36b22835e988cc94b06b52c428b32212db5b961c8975570aa7c9ebeac4149593", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2658b3d42b275060546a2e4d9d93fc03109a6ea5f2765015fc13a904d3ef45b7", "generation_seconds_batch": 14.883427757071331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8696303367614746, "target_z": 1.281249996472371, "ce": 5.7247633934021, "genuineness": 4.068024158477783, "identity": 0.559630274772644, "hypothesis": "J'ai trouvé la 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_Triumph/36b22835e988cc94b06b52c428b32212db5b961c8975570aa7c9ebeac4149593.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": "36e33ff7e973746dc8642f8fdb935a572e285d7474a8dc9511fc724e780025b7", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "348fb824f478bf045baabc97ba5f9c83aa194adb74d1549035d2e7320ead75ee", "generation_seconds_batch": 19.291107820929028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1840859353542328, "target_z": -0.017089839175105977, "ce": 5.990842819213867, "genuineness": 4.174716949462891, "identity": 0.7425543665885925, "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_Triumph/36e33ff7e973746dc8642f8fdb935a572e285d7474a8dc9511fc724e780025b7.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "370e83ad916eec7d136589a7bd7271d507089256e72ee08fc4b4797195ca1fae", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a89190a415109035965b1c2c750ebe64e16b97658755425a7cd754a2e7d43471", "generation_seconds_batch": 19.49327563296538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5045566558837891, "target_z": 0.5898437186922915, "ce": 6.252951145172119, "genuineness": 4.607763767242432, "identity": 0.6961904764175415, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/370e83ad916eec7d136589a7bd7271d507089256e72ee08fc4b4797195ca1fae.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "37636b3e3769512d0383a677dff792df40d4891c993fec118d5cef20a8a276d6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b7ec3437f3d2961f88253d967779ae4ff3960cd3e7d0f8339c6b27102757fedf", "generation_seconds_batch": 19.81414028594736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23951731622219086, "target_z": 0.08789062566143047, "ce": 6.24500846862793, "genuineness": 4.482243061065674, "identity": 0.7529972791671753, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/37636b3e3769512d0383a677dff792df40d4891c993fec118d5cef20a8a276d6.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "3773b7d2b67bbc8226e7d7e924d780a3d7ba7f038fb2b7d76902939f2acf6507", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "265c02759136819dd55a31372476e3e075dc6eb5c09e7b5b46ed025e3e36e07b", "generation_seconds_batch": 21.674069302040152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2683931887149811, "target_z": 0.142578105377563, "ce": 6.2767791748046875, "genuineness": 4.444586753845215, "identity": 0.443965345621109, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3773b7d2b67bbc8226e7d7e924d780a3d7ba7f038fb2b7d76902939f2acf6507.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "37c6fe0dfd8f8b93ea2795af688ab7e0582186eb29e8357ddc93e7e4204ee34c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "55ea105b4abf8cf99e6451de1beb93b61371f94cdda84238932a3edd9540b65b", "generation_seconds_batch": 19.44722157297656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3931782841682434, "target_z": 0.3789062848353376, "ce": 6.1894097328186035, "genuineness": 4.143336772918701, "identity": 0.44642511010169983, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/37c6fe0dfd8f8b93ea2795af688ab7e0582186eb29e8357ddc93e7e4204ee34c.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": "383700b2c76a3aea9ad4d195804f1a7da70b07e49959bdb08f85d810f37f3c34", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The keys are on the kitchen table.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34bb7296b5cd49ba7f804c870f45ddb9541b6e598be5a6a52118cbc91dc45c20", "generation_seconds_batch": 16.92890536505729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22611065208911896, "target_z": 0.06249999294474175, "ce": 6.109982967376709, "genuineness": 3.9173994064331055, "identity": 0.34894099831581116, "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_Triumph/383700b2c76a3aea9ad4d195804f1a7da70b07e49959bdb08f85d810f37f3c34.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "388557e44763a7b4755750cccb6769d43b3f25d11a624a9373913f47fa36c9d5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "39ea42b97834a620ee2429f04fc62da64c70083f12c979a0c9815b95f768d260", "generation_seconds_batch": 20.322990825981833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16861671209335327, "target_z": -0.0463867143955828, "ce": 6.268836498260498, "genuineness": 4.356721878051758, "identity": 0.5395427346229553, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/388557e44763a7b4755750cccb6769d43b3f25d11a624a9373913f47fa36c9d5.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "38e86595fe653b0611381e592d2ed675462a5b4a5772ba01bc6d06c6d8a35832", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "33ef1556611759587786533e6995d9510df1f6af1515d100b0a9882378d06391", "generation_seconds_batch": 14.893984192982316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8761610984802246, "target_z": 3.1874999506131925, "ce": 5.673136234283447, "genuineness": 3.7667744159698486, "identity": 0.24702595174312592, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/38e86595fe653b0611381e592d2ed675462a5b4a5772ba01bc6d06c6d8a35832.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "38fab3a3fbc95c412cffc540543609c9bf85a01f13f7e41ebfbd5e5e563b2f89", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c2e350abc46fed8e92d862f18654bebee78ece6b782cca65c704c4545a153d83", "generation_seconds_batch": 19.47824438905809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1443815976381302, "target_z": -0.09228514847819208, "ce": 6.197352409362793, "genuineness": 4.005263805389404, "identity": 0.2854885458946228, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/38fab3a3fbc95c412cffc540543609c9bf85a01f13f7e41ebfbd5e5e563b2f89.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "3945483d9659215d9a2c4a518ff3796646c154d239b4bbd2133f5c5640ceb53c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ee9090d4fbcc135ae9fe699b13e9fa19732d75b421a297c28260d25fb5aa438", "generation_seconds_batch": 15.269302716013044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5169320702552795, "target_z": 0.6132812865991522, "ce": 5.982900142669678, "genuineness": 3.7542223930358887, "identity": 0.5229777097702026, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3945483d9659215d9a2c4a518ff3796646c154d239b4bbd2133f5c5640ceb53c.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "395e2db49fe41d2ff606e7bc7f8b07204f0f8c2fc39fbde82d90bf7aa417b219", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "66d26807f444a8a4676a4a31563af8b4994bc62a76ce66e1419142a36e56391a", "generation_seconds_batch": 20.349636319093406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0882620811462402, "target_z": 1.6953126049469665, "ce": 5.982900142669678, "genuineness": 4.281409740447998, "identity": 0.5682742595672607, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/395e2db49fe41d2ff606e7bc7f8b07204f0f8c2fc39fbde82d90bf7aa417b219.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "3975959784fae003cc70ddfb4ffbaee47fe9258b13ecee9e67dc7e5f0e1934d8", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1bb0e870e317627bfca4acb12f3ad76dcac1da66c37d8a4f6af7fd86fae3f275", "generation_seconds_batch": 20.734853558940813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6984375715255737, "target_z": 0.9570311913531658, "ce": 6.173524379730225, "genuineness": 4.557555198669434, "identity": 0.4591701626777649, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3975959784fae003cc70ddfb4ffbaee47fe9258b13ecee9e67dc7e5f0e1934d8.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "399885d7fcb3bd3499c34c509b208fe22f4b2fd006f7a5cdc99e00f357cb27e4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "38a86b399c0eaf43e6654c7c87148c03988ea147e1ef0fd037594cbda0eba247", "generation_seconds_batch": 21.27039734099526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7953780293464661, "target_z": 1.140624927683603, "ce": 6.109982967376709, "genuineness": 4.413206577301025, "identity": 0.5969096422195435, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/399885d7fcb3bd3499c34c509b208fe22f4b2fd006f7a5cdc99e00f357cb27e4.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "39af3b952103da447059eca7d67da8dfd55591dfd116775d5d3e6a414e8d5114", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f19f72ac562192862d4379f4fdb10c80f366e7e3b7b372a75dc9dcc7fbf1a352", "generation_seconds_batch": 14.793119069072418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3519269824028015, "target_z": 0.30078120899131144, "ce": 6.23706579208374, "genuineness": 4.507347106933594, "identity": 0.6271113157272339, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/39af3b952103da447059eca7d67da8dfd55591dfd116775d5d3e6a414e8d5114.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "39c4f68ad91a6897716bc1c54c7c3fa92a852e87113fa06fdd48fa36f1159ed7", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9328af8107fe7d01fd72edcf11eb7eca09ae0f275fedf76aa72de0ad9226245f", "generation_seconds_batch": 20.322990825981833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2467362880706787, "target_z": 0.10156250264572185, "ce": 6.300607204437256, "genuineness": 4.344170093536377, "identity": 0.6580575108528137, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/39c4f68ad91a6897716bc1c54c7c3fa92a852e87113fa06fdd48fa36f1159ed7.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "39f0a5d6da08559cce06dd5ef1ac9abf42bf6c10e1d3217eac55f72880855f21", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "81b0058ec52f863c6ebacf7555c42324b5cd6d31d9bacd8ba5fc8832a0d98ab5", "generation_seconds_batch": 21.072849304997362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0016343593597412, "target_z": 1.5312499682513379, "ce": 5.998785495758057, "genuineness": 4.344170093536377, "identity": 0.6497924327850342, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/39f0a5d6da08559cce06dd5ef1ac9abf42bf6c10e1d3217eac55f72880855f21.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "39fdc50ac6552d0fe4bb65a532362a80c9d5c878611365061300fadfc8b95a93", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1b3f839a4b4019e22438ed2ac67c05f27adf3ede567cd592650a29dcc131e84c", "generation_seconds_batch": 19.470512664993294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6427484154701233, "target_z": 0.8515625308667548, "ce": 5.736677646636963, "genuineness": 4.005263805389404, "identity": 0.40538203716278076, "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_Triumph/39fdc50ac6552d0fe4bb65a532362a80c9d5c878611365061300fadfc8b95a93.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "3a1503ca8a73c7aa30a48114be4fd9dc0840e07a055bde296fa738d5d7ad6405", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3e3f44ceb829caa412ee7f84f44bdaaa275aa38002e3a19f2a8deb6365e00fc0", "generation_seconds_batch": 15.251963375951163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3646454811096191, "target_z": 2.2187500035276293, "ce": 5.629451274871826, "genuineness": 4.2751336097717285, "identity": 0.5627219080924988, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3a1503ca8a73c7aa30a48114be4fd9dc0840e07a055bde296fa738d5d7ad6405.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": "3a207516d35c36d5a081efe764415c7f028db0b598a0732ebc7263d4cc65cc11", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fb6a6435bb4ee80c1904ad6c01eca77a0a7d5b8827ad0af74cdce6d9257a0e5", "generation_seconds_batch": 20.353582159033976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8943811058998108, "target_z": 1.3281250194019603, "ce": 6.2767791748046875, "genuineness": 4.381826400756836, "identity": 0.6307576298713684, "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_Triumph/3a207516d35c36d5a081efe764415c7f028db0b598a0732ebc7263d4cc65cc11.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "3a7fb87d57e449c08e62a292dda204dcfc279c145dfa90d9fe2a2ca5b2dda951", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "02d9b5cb1831749b76e61947c65ebbb17f0eccc0e7d2c7407b0d00d875e9a60c", "generation_seconds_batch": 20.151852617040277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49011874198913574, "target_z": 0.5625000211657748, "ce": 6.0146708488464355, "genuineness": 4.344170093536377, "identity": 0.6285181641578674, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3a7fb87d57e449c08e62a292dda204dcfc279c145dfa90d9fe2a2ca5b2dda951.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "3add62e1a8e133e896648484a93b463d66a335358901513240415a2976bd7380", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b1aa5476b542ef097310b86f390f48e78d4b4a6fdf48d932fd0f7caef97bcc4f", "generation_seconds_batch": 21.50377768895123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6451539993286133, "target_z": 2.749999887115868, "ce": 5.5539960861206055, "genuineness": 3.923675537109375, "identity": 0.6206820011138916, "hypothesis": "La porte est encore ouverte ! J'ai posé ton manteau sur la chaise ! Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3add62e1a8e133e896648484a93b463d66a335358901513240415a2976bd7380.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "3b703656d25f6309299d846117b45a5c2cec788313109f72f0f446705d9a54aa", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "446f9ffc1e7e2b5518b51a2ed1c860a79fb598b010eebbe1779bd9b1d61f60fe", "generation_seconds_batch": 20.72033326898236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4801490306854248, "target_z": 2.437500035276291, "ce": 6.1020402908325195, "genuineness": 4.432034492492676, "identity": 0.4121701717376709, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3b703656d25f6309299d846117b45a5c2cec788313109f72f0f446705d9a54aa.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": "3bad52d382d252e33112b403bdf8ef074c0834a54e346694809a82789759c7e1", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a87989ad39331ff65a20e9083301c560075ee6185040dae01b5f60d0566b915", "generation_seconds_batch": 18.982315207016654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08173123747110367, "target_z": -0.2109375044095364, "ce": 6.23706579208374, "genuineness": 4.256305694580078, "identity": 0.6916218996047974, "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_Triumph/3bad52d382d252e33112b403bdf8ef074c0834a54e346694809a82789759c7e1.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "3bc111d3727b17a20ee27cf707e73d7805624611caee38e74865df89e1904554", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3e55674b3afb99e3bdc58a05588bf7e95e1f41ae6223cc7e27d19a33140bcc0c", "generation_seconds_batch": 19.347679002094083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07657483220100403, "target_z": -0.22070312477952317, "ce": 6.141753673553467, "genuineness": 4.821148872375488, "identity": 0.6121623516082764, "hypothesis": "J'ai trouvé la petite boîte, elle était près, de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3bc111d3727b17a20ee27cf707e73d7805624611caee38e74865df89e1904554.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "c9a1c17664e6226953cc52d6bc61b94bce5a3424d4a90b69a7f630fbd14009a1", "generation_seconds_batch": 15.16460825491231, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0729653462767601, "target_z": -0.22753906327166887, "ce": 6.356205940246582, "genuineness": 4.406930446624756, "identity": 0.6955123543739319, "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_Triumph/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "3c9f8583b96b67f3bd9b07b8aceaed8932bae51f7c62f371192b8aa13a64276b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cad814c3ddb2c7ca50656c9683fe9095dc54fd48c37032f00a5b386133ddd92e", "generation_seconds_batch": 21.155730706988834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41071003675460815, "target_z": 0.4121093461175365, "ce": 5.752562999725342, "genuineness": 4.005263805389404, "identity": 0.2815788984298706, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3c9f8583b96b67f3bd9b07b8aceaed8932bae51f7c62f371192b8aa13a64276b.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "3cc2f62364ebac8e227f1706ba027eb0f5b50c3819d51c54fae4bdd41aaea270", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4b1f92f1d72116e9d6e10e4f74f64ad6383a5a070f4582999cfabe8d9d0ba35a", "generation_seconds_batch": 21.7691732380772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.509711265563965, "target_z": 6.281250335124767, "ce": 5.363371849060059, "genuineness": 3.7542223930358887, "identity": 0.530307948589325, "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_Triumph/3cc2f62364ebac8e227f1706ba027eb0f5b50c3819d51c54fae4bdd41aaea270.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "3cd1f3fd82508ea919e3ab8318a975f597813418ee5a00291ae659c4a9499d99", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2efa2a8b135086df81978375919ba380b5ec167908a6e88df9e425b53155d56a", "generation_seconds_batch": 21.430692394962534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24312680959701538, "target_z": 0.09472657826409266, "ce": 6.09409761428833, "genuineness": 4.124508857727051, "identity": 0.7436951398849487, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3cd1f3fd82508ea919e3ab8318a975f597813418ee5a00291ae659c4a9499d99.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": "3e0779d9ca41a320fa46f31f20fb685d0a35301cae0c2a983d943cd1dd59c593", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d272bb4892e955b7d3f1f03010e8100b819bbafd77dbdb36ca5cc36d6a5e916", "generation_seconds_batch": 16.89781374996528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12865453958511353, "target_z": -0.12207033223267542, "ce": 6.229123115539551, "genuineness": 4.482243061065674, "identity": 0.7018041610717773, "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_Triumph/3e0779d9ca41a320fa46f31f20fb685d0a35301cae0c2a983d943cd1dd59c593.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "3e479b2a04b40870f1385081ae3001c5f23a42ffacfd2131a5cc022945d7fc7b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1e1a9b8452983f60718b47173a44a02caa9b99cb4cbd5ae462e36795bcd797ff", "generation_seconds_batch": 14.799336500000209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0098845958709717, "target_z": 1.5468749382664904, "ce": 6.133810997009277, "genuineness": 4.293961524963379, "identity": 0.6718363761901855, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3e479b2a04b40870f1385081ae3001c5f23a42ffacfd2131a5cc022945d7fc7b.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "3eb6b39f0feb6981a6212e6b3579ba391bf6b73dea70985b7d6d80651e19fc44", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "43327c24b3703295e37a428d7014058bd143a091ff0e38660974c9c51e41d1ee", "generation_seconds_batch": 22.340880049974658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.443709135055542, "target_z": 6.15625012346702, "ce": 6.213237762451172, "genuineness": 3.798154592514038, "identity": 0.2775983512401581, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3eb6b39f0feb6981a6212e6b3579ba391bf6b73dea70985b7d6d80651e19fc44.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "3f1dfd5a3ee9c4456252c829f91928824c6ad9bc4f24e5639a99ff7bf5ca3eb0", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ebcc8151cb3bda8bd2c61366a55866b81b7c933d9c536e30398258f1b1cb037f", "generation_seconds_batch": 21.50529074005317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8761610984802246, "target_z": 3.1874999506131925, "ce": 6.427689552307129, "genuineness": 4.080576419830322, "identity": 0.4462957978248596, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/3f1dfd5a3ee9c4456252c829f91928824c6ad9bc4f24e5639a99ff7bf5ca3eb0.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": "3fbc7a37a7083ef7e4883ac3446cce2a83b69f75b5275d70ae2a5aa2c1a50e91", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Escribí el número en el sobre.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93b6462965f7d3c5526dad428aa540577685daeea313fbfed5bb64bd76907c35", "generation_seconds_batch": 21.262886692071334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9751641750335693, "target_z": 3.3750000423315494, "ce": 6.117925643920898, "genuineness": 4.055472373962402, "identity": 0.7948523759841919, "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_Triumph/3fbc7a37a7083ef7e4883ac3446cce2a83b69f75b5275d70ae2a5aa2c1a50e91.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "40515be1fc2391fa673bb42caba45dd37975f46ed359b24c7ed365138db9ec91", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "166415b1eda39881d42bff206dc002e8465563a65175d0bb28855a72f6eba986", "generation_seconds_batch": 21.876155265024863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5643709897994995, "target_z": 0.7031249770704107, "ce": 5.990842819213867, "genuineness": 4.15588903427124, "identity": 0.35981208086013794, "hypothesis": "I found the little box! It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/40515be1fc2391fa673bb42caba45dd37975f46ed359b24c7ed365138db9ec91.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "40c105a989501efc7b63a0a241c3785227e78a8c213012407bb0ceb6f2af9e4c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "13afc7225e57edb1170c8e6edb652053d7ccf1768eaa77a67cadef9f3dd36ed1", "generation_seconds_batch": 19.336537839029916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.942163109779358, "target_z": 3.3124999365026757, "ce": 6.459460258483887, "genuineness": 4.124508857727051, "identity": 0.4526365399360657, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/40c105a989501efc7b63a0a241c3785227e78a8c213012407bb0ceb6f2af9e4c.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "41b062772da5dff3c5d051956dbd12c06603e6e222346e2c94cbce62e125ad11", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0062079198c25a5a0dfaacbd3cabe4c59ba1f939be04f327d6aba8aa350c5eab", "generation_seconds_batch": 15.953835360938683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4550551772117615, "target_z": 0.4960937857172449, "ce": 6.221180438995361, "genuineness": 4.319066047668457, "identity": 0.4621022939682007, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/41b062772da5dff3c5d051956dbd12c06603e6e222346e2c94cbce62e125ad11.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "42087e3a66f342cc9b3e8c55a45b40b76567e84cef42862480356e613e226f79", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6224fd6cb6f45c5bd2dc356ae702e905ffb9a5e38a8d8fbb8aae36a3d6f6a4d0", "generation_seconds_batch": 17.199481320916675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5361814498901367, "target_z": 4.437500261044555, "ce": 6.252951145172119, "genuineness": 3.886019229888916, "identity": 0.2859868109226227, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/42087e3a66f342cc9b3e8c55a45b40b76567e84cef42862480356e613e226f79.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "425ce66911373c2f10e15e5ed6c8bb47bb862652fe806f793b74bd8bb4ad1603", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "efbd20cf2be5448a4fa2a487d4456d587b923984b325cbac79f6e45dad1055f6", "generation_seconds_batch": 22.079803666914813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1171379089355469, "target_z": 1.75, "ce": 5.7128496170043945, "genuineness": 4.105680465698242, "identity": 0.7135716080665588, "hypothesis": "Tu trouvais la petite boîte ? Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/425ce66911373c2f10e15e5ed6c8bb47bb862652fe806f793b74bd8bb4ad1603.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "426b241e65582568e6af4ada068de78314603077c25bb73b78b6e3e38895bd42", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de65d6a1b8f6413ece2994e4629f5e34d1005fa007bb0a3d54ab8554c9d197c2", "generation_seconds_batch": 20.231967589003034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1399986445903778, "target_z": -0.10058594201977482, "ce": 6.173524379730225, "genuineness": 3.898571252822876, "identity": 0.25028157234191895, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/426b241e65582568e6af4ada068de78314603077c25bb73b78b6e3e38895bd42.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "2ef26b85b008fd26a595cafd61b8f22b8e7cce784243561e98f1c2b0f4fb577f", "generation_seconds_batch": 14.80683101597242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07915303856134415, "target_z": -0.21582030753927153, "ce": 5.9431867599487305, "genuineness": 4.400654315948486, "identity": 0.5425586700439453, "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_Triumph/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "4352f58918bb6b66a82010eaa4da9c108d0d562224f47ae4b4195ac99ba015ee", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e5c6406494e8c908390e3f07f6579ba0aedb13a8137b1f6ab69756bb3a46fe4", "generation_seconds_batch": 19.504834538907744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5024940967559814, "target_z": 0.5859374761885034, "ce": 6.284721851348877, "genuineness": 4.645420074462891, "identity": 0.6308164000511169, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4352f58918bb6b66a82010eaa4da9c108d0d562224f47ae4b4195ac99ba015ee.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": "43bbf59e863accc368923fa54f41b45c08e3080046efd90f0325541e7dedcaa2", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e85dea88a2e6c3c90904ee56aaec2713c00a34d10bd6570faface42b7415b14", "generation_seconds_batch": 17.65027819701936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8514103889465332, "target_z": 3.140625040567735, "ce": 6.125868320465088, "genuineness": 4.65797233581543, "identity": 0.7990916967391968, "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_Triumph/43bbf59e863accc368923fa54f41b45c08e3080046efd90f0325541e7dedcaa2.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "38685206e93965f0fce8ddb81c9a4f8c124c5efbc91620cb6b72d38b8b94e6d7", "generation_seconds_batch": 16.01942240295466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.056980475783348083, "target_z": -0.2578125132286092, "ce": 6.3641486167907715, "genuineness": 4.545003414154053, "identity": 0.48979926109313965, "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_Triumph/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "4415a700581efcc4787b39e5d85f7ad20d9b3035e2870b080752e9e708f858c9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f0c97e7eab79de885a5f5e21d7e93ab5584914cce9e3d95a8584ceb7b6b77faa", "generation_seconds_batch": 20.991633152007125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7458765506744385, "target_z": 1.0468749947085563, "ce": 6.213237762451172, "genuineness": 4.18099308013916, "identity": 0.49277350306510925, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4415a700581efcc4787b39e5d85f7ad20d9b3035e2870b080752e9e708f858c9.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "4427e64a7ee7ea184d626d546195edcf099655bc4469fa20c2ca0658108ff791", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6a3a00e81c51b1e6b2481a78497bad2b6548fcafc2f82e957891290f45a830ea", "generation_seconds_batch": 21.032102541066706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.073480986058712, "target_z": -0.22656250264572184, "ce": 6.157639026641846, "genuineness": 4.7081804275512695, "identity": 0.7260767221450806, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4427e64a7ee7ea184d626d546195edcf099655bc4469fa20c2ca0658108ff791.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "4458e5fb8812bed3d02b428452d81fa8621d086ffb4b33ca7c876438bac4983d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c86a21ac4254e236854c3e0490751d911ffc30dd995c754174d2570eefb404e3", "generation_seconds_batch": 19.448202500934713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13716262578964233, "target_z": -0.10595702546248346, "ce": 6.292664527893066, "genuineness": 4.369274139404297, "identity": 0.6842902898788452, "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_Triumph/4458e5fb8812bed3d02b428452d81fa8621d086ffb4b33ca7c876438bac4983d.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": "447b7839cf74af24e517301182da2d79171f6e797083273c261884a97df8e140", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80d7445f57c5c6a0f171f8e57156008cb4259b45468bcd2627709e7bd4b4a710", "generation_seconds_batch": 19.950618352973834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4718987941741943, "target_z": 2.4218750652611387, "ce": 6.348263263702393, "genuineness": 4.519899368286133, "identity": 0.4592670202255249, "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_Triumph/447b7839cf74af24e517301182da2d79171f6e797083273c261884a97df8e140.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "449a1fe418d42c7ab6ba2136de30e488d2fe7a726fd02c5c483e96de9e30223e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7f770d680b20b172d7a465ffd72a0ff09a3ab8d55cedd3bd40d55fa2e52bbcdd", "generation_seconds_batch": 21.121452855993994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.727656602859497, "target_z": 2.9062500388039205, "ce": 5.367343425750732, "genuineness": 3.8420867919921875, "identity": 0.5612332820892334, "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_Triumph/449a1fe418d42c7ab6ba2136de30e488d2fe7a726fd02c5c483e96de9e30223e.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": "44c835cabf7426430cb6215f6d0d087e9b7480c6eb43a135d7519b9f91c5168e", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d386084aa1b54399ffeb5589f8599fffbdc57cfca955617945c486669e266b5d", "generation_seconds_batch": 14.877552654943429, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3151439428329468, "target_z": 2.1249999576684506, "ce": 5.8875885009765625, "genuineness": 4.21237325668335, "identity": 0.7131969928741455, "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_Triumph/44c835cabf7426430cb6215f6d0d087e9b7480c6eb43a135d7519b9f91c5168e.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "44cc036b0c7fe9800283c9c5f890909956fa6c32f32f0bd5d116f5ed44ae81b3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd681a1d66cc482d26d062468e0d4a0e009f7f66824b2715ce9d30a4694a6115", "generation_seconds_batch": 21.247129102936015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3316444158554077, "target_z": 2.156249897698755, "ce": 6.181467056274414, "genuineness": 4.13078498840332, "identity": 0.3083072304725647, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/44cc036b0c7fe9800283c9c5f890909956fa6c32f32f0bd5d116f5ed44ae81b3.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "44d759d59028d4a7bed92775add45bbcf7f88134b9a1eb8920ce55e0e74f4c8b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "be670f7717531492bd03ea26ca104cbc11b09ac6f735059d6e107914ce3cfd74", "generation_seconds_batch": 23.37577424303163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3132539391517639, "target_z": 0.22753904916115236, "ce": 6.078212261199951, "genuineness": 4.21237325668335, "identity": 0.44648367166519165, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/44d759d59028d4a7bed92775add45bbcf7f88134b9a1eb8920ce55e0e74f4c8b.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": "45a00aa72fbc9aaf63c857d6e3babbf1f2ca9af740570955b9a4a6706dfdae52", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d8ed9938afd465d5fd45611267aed1d4eaeb6b839bd145589a613afc9e76c703", "generation_seconds_batch": 19.923370825941674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9174124002456665, "target_z": 3.2656250264572186, "ce": 6.133810997009277, "genuineness": 4.444586753845215, "identity": 0.3676852285861969, "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_Triumph/45a00aa72fbc9aaf63c857d6e3babbf1f2ca9af740570955b9a4a6706dfdae52.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "45e821f1f70189663587ac592ff2fe5b720abad42439a90ff1cb5986b29518d3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bf5ac1d22281e5f67fb896a5e55acf7e3c40801166a75eaeb25f766cb3ec5757", "generation_seconds_batch": 22.97900382790249, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5519956350326538, "target_z": 0.679687522047682, "ce": 6.1894097328186035, "genuineness": 3.948779582977295, "identity": 0.3818632662296295, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/45e821f1f70189663587ac592ff2fe5b720abad42439a90ff1cb5986b29518d3.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "42fd821926ff8acce7f80af87c613f3713e4c31e677793ffa36ca39fe0d1a55c", "generation_seconds_batch": 16.15537664690055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2725183367729187, "target_z": 0.1503906468272052, "ce": 6.229123115539551, "genuineness": 4.406930446624756, "identity": 0.6849449872970581, "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_Triumph/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "45fa6ec8d73215c12f2decaf08022f2b3961cd6eb9ba6f4cd94adea25c034826", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ff87d7dc6c6369d5e1412a2b747348ea92679d2dee41e77db00e0195d1cf3d22", "generation_seconds_batch": 21.40187646704726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25086140632629395, "target_z": 0.10937498765329806, "ce": 6.086154937744141, "genuineness": 3.653805732727051, "identity": 0.4425838887691498, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/45fa6ec8d73215c12f2decaf08022f2b3961cd6eb9ba6f4cd94adea25c034826.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "462a724f71f5d013c4b24fc1729540bc8210d84e930bc440f670ac24bd4c25e3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "35095ddfe699eb35b33c8365d340d0ba60e91ae709737099112223c4347db7a9", "generation_seconds_batch": 19.21245148498565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23152488470077515, "target_z": 0.07275390773821853, "ce": 6.324435234069824, "genuineness": 4.557555198669434, "identity": 0.4595211148262024, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/462a724f71f5d013c4b24fc1729540bc8210d84e930bc440f670ac24bd4c25e3.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "463f2a383377f05b89cd32e4c8e7affa91c3ec1df092698832c7e8fdda36f13c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8caf9231a925e8fcb46e88e8e7738a8d05b6551287c21fb4574fcd1a39522745", "generation_seconds_batch": 21.605198413017206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.607684850692749, "target_z": 0.785156295418225, "ce": 6.125868320465088, "genuineness": 4.469690799713135, "identity": 0.49317672848701477, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/463f2a383377f05b89cd32e4c8e7affa91c3ec1df092698832c7e8fdda36f13c.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "466a0bf94c3361a608db7a6677f7333e96940938693ed53e33cacb72a81789bb", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "807358309eb198d13242fbb6b22742b3f86846cd63e974055e9f43e3fdcf3527", "generation_seconds_batch": 21.575901863048784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.509711265563965, "target_z": 6.281250335124767, "ce": 5.788304805755615, "genuineness": 4.093128204345703, "identity": 0.2236168533563614, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/466a0bf94c3361a608db7a6677f7333e96940938693ed53e33cacb72a81789bb.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "473bdb23245d0fa005f2225550862a65c17bab1be2fc744ea51f1e7387a449ab", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ad4f997741c93227629223d69002c56b2457947da53c62a7263769e4890c2060", "generation_seconds_batch": 22.438804582925513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37255263328552246, "target_z": 0.33984374691332453, "ce": 5.863759994506836, "genuineness": 3.7291181087493896, "identity": 0.511236310005188, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/473bdb23245d0fa005f2225550862a65c17bab1be2fc744ea51f1e7387a449ab.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": "4765f6ddb5beb45f5a29e0e818e1872b7111bf594cf665cc700eb7820aa54b57", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a54d39a4372f12e177a286915aaeabadccf78f23384792eb8053e7ce872fabd", "generation_seconds_batch": 16.20720156095922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6633740067481995, "target_z": 0.890624955904636, "ce": 6.308549880981445, "genuineness": 4.3504462242126465, "identity": 0.34837794303894043, "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_Triumph/4765f6ddb5beb45f5a29e0e818e1872b7111bf594cf665cc700eb7820aa54b57.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "47ba7153b694a8b05cc9f2d74c9bc538046d077fb3629e4a44f21dcbd1c0346a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "555565b38e12c9dc47b95bf2a0387c8f3f112a36e2b111b75649fa018062383c", "generation_seconds_batch": 22.340880049974658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.833190441131592, "target_z": 5.000000084663099, "ce": 6.157639026641846, "genuineness": 3.9801597595214844, "identity": 0.08260669559240341, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/47ba7153b694a8b05cc9f2d74c9bc538046d077fb3629e4a44f21dcbd1c0346a.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "ccc7f83b11b9897511324ced849f2650006a56846178094f0809b10389367abf", "generation_seconds_batch": 14.852656758041121, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0069589763879776, "target_z": -0.3789062566143046, "ce": 6.1894097328186035, "genuineness": 4.444586753845215, "identity": 0.7850285768508911, "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_Triumph/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "47d3f9e993b073aa24cbf015047f0d5e681e8bc1c02bbd333ca89e0d7832f1ea", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e9dea7d4b2f47554fa6825bb1b9fd8ea186717114a3b23ab1a7002ffd53ec60a", "generation_seconds_batch": 20.773968784022145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22611065208911896, "target_z": 0.06249999294474175, "ce": 6.0146708488464355, "genuineness": 3.6349775791168213, "identity": 0.37311694025993347, "hypothesis": "The door is still open! I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/47d3f9e993b073aa24cbf015047f0d5e681e8bc1c02bbd333ca89e0d7832f1ea.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": "484734771a66dd52cdbe119171248385a23dcdc162b5aab1804412c0e575e3dc", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The keys are on the kitchen table.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3ad98a696a3ca2ab19b52baa91b3641449b8868ecba5b5d21d14c3b2ab22711", "generation_seconds_batch": 19.10334942000918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06316816806793213, "target_z": -0.2460937574962119, "ce": 6.348263263702393, "genuineness": 4.149612903594971, "identity": 0.4190966486930847, "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_Triumph/484734771a66dd52cdbe119171248385a23dcdc162b5aab1804412c0e575e3dc.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "48542e8a3cb53a2d61db1a345f85f985097800b63814a6b11c63d6d215b872f2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e121aefd594b38fce9e0d3584786c71c380abe3f93fc5ac77421594209c952f", "generation_seconds_batch": 20.85492881992832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3132539391517639, "target_z": 0.22753904916115236, "ce": 6.205295085906982, "genuineness": 4.030367851257324, "identity": 0.411258727312088, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/48542e8a3cb53a2d61db1a345f85f985097800b63814a6b11c63d6d215b872f2.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "48a26aaceaa52c89d25768e38eebfc029008ebcaef7d1cbf7235e4c1d0497bde", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dd02b5706479c120a6c4f5ebcb13e6698fe811f54c71a15a9995d305e25421a4", "generation_seconds_batch": 21.288842648034915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6468735337257385, "target_z": 0.8593750158743311, "ce": 6.070269584655762, "genuineness": 4.444586753845215, "identity": 0.5681060552597046, "hypothesis": "J'ai trouvé la petite boîte. Elle était prêde, la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/48a26aaceaa52c89d25768e38eebfc029008ebcaef7d1cbf7235e4c1d0497bde.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "4945845d7bdaf14a57a5cb53331a77c8a9d618029279296c9bcc4fd76250db4a", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b7337f31b0180729e60ef3f6eabc7039bf0689868eb5eae1b512a063762961db", "generation_seconds_batch": 15.777106701978482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2962377965450287, "target_z": 0.19531249206283446, "ce": 6.284721851348877, "genuineness": 4.6203155517578125, "identity": 0.3980520963668823, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4945845d7bdaf14a57a5cb53331a77c8a9d618029279296c9bcc4fd76250db4a.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "494a859c9c7b58487f8a0e2df9c0dacdb33c78a31c26b3553d3062077be770fd", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d616f1011a4fbaa83013aa41a3ccddac1b78a5d773a58632800df996732ffa8c", "generation_seconds_batch": 21.247129102936015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0552610158920288, "target_z": 1.6328124991180928, "ce": 6.070269584655762, "genuineness": 4.068024158477783, "identity": 0.5477733612060547, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/494a859c9c7b58487f8a0e2df9c0dacdb33c78a31c26b3553d3062077be770fd.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": "4999b718c4270a1c808692e18c9dbed236dd5b6e8fcb21b98bfb52c19306fef3", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5ad5a67669660c7e5ac02b70af974f8409aec86c6eb1a729da23ad4e67f4a83", "generation_seconds_batch": 16.597467512008734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5148695111274719, "target_z": 0.609375044095364, "ce": 6.1020402908325195, "genuineness": 3.9299514293670654, "identity": 0.4179413914680481, "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_Triumph/4999b718c4270a1c808692e18c9dbed236dd5b6e8fcb21b98bfb52c19306fef3.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "703faa276b140ab46d711ed83e7752aced983f3d3606422e21fabbb792007e5f", "generation_seconds_batch": 14.770697762956843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1250450611114502, "target_z": -0.1289062566143046, "ce": 6.213237762451172, "genuineness": 4.093128204345703, "identity": 0.595810055732727, "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_Triumph/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "4a0fe95e94db21afbd9151205859d761e4cc39ddf66966a705d7ec01ce24535e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "74eb005f11c408c9c958075597fac073b207abe9b6c71c1644d05f7b3652c032", "generation_seconds_batch": 20.276309912092984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11576353013515472, "target_z": -0.1464843761023841, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.5858099460601807, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4a0fe95e94db21afbd9151205859d761e4cc39ddf66966a705d7ec01ce24535e.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": "4a453ac1bb98f09da2466b992612a48a817feafde1e629e1091d4b994d9892f3", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe7c564978281eb5d0fc90287b142153553b0efcb9d16ad1418425039823951f", "generation_seconds_batch": 19.334014646010473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14670197665691376, "target_z": -0.08789062566143047, "ce": 6.316492557525635, "genuineness": 4.469690799713135, "identity": 0.3746834099292755, "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_Triumph/4a453ac1bb98f09da2466b992612a48a817feafde1e629e1091d4b994d9892f3.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "4aa5427286a43099ab476cd062564ce67bc8bce8bf521314f0123be1c997b189", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b877c7014df71e98e5e5f18470cd9c80e8964af50f69c5a1e0c57d792b47efcf", "generation_seconds_batch": 21.072849304997362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8761610984802246, "target_z": 3.1874999506131925, "ce": 6.395919322967529, "genuineness": 4.482243061065674, "identity": 0.6148535013198853, "hypothesis": "J'ai trouvé la 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_Triumph/4aa5427286a43099ab476cd062564ce67bc8bce8bf521314f0123be1c997b189.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "4b2b4f09e16f907099ada4801fc36b91483b1616ac46f23c90456853e36f2440", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "87c55d8022136ca92d2e0e7bebf84b4b02bf2494675c809467ee58e34e8d8be6", "generation_seconds_batch": 20.073796384967864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2585960328578949, "target_z": 0.12402345348456947, "ce": 6.109982967376709, "genuineness": 3.8044304847717285, "identity": 0.5416203737258911, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4b2b4f09e16f907099ada4801fc36b91483b1616ac46f23c90456853e36f2440.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "4b766087748be1b527ff7884bd63beb4c8b8bae145f5d4fdcb308e25212f5520", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8dde3048fb41bc4d4e693d1a3eacd4fa885b484381f1f0c01a92145561565cb4", "generation_seconds_batch": 14.846591594978236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.179701089859009, "target_z": 5.656250179909085, "ce": 6.117925643920898, "genuineness": 4.042920112609863, "identity": 0.30469751358032227, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4b766087748be1b527ff7884bd63beb4c8b8bae145f5d4fdcb308e25212f5520.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": "4bb17cce9da6e6cd511f9bce5a16a3c62aa94d3940dd7fac8cabb3f30094098e", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8442fb2b9517f75571889a8ea367251fa54155394c7465ff59b7294fcfc2d9fc", "generation_seconds_batch": 16.288600826985203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9999148845672607, "target_z": 3.421874952377007, "ce": 6.078212261199951, "genuineness": 4.074300289154053, "identity": 0.5470974445343018, "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_Triumph/4bb17cce9da6e6cd511f9bce5a16a3c62aa94d3940dd7fac8cabb3f30094098e.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "4bd24f421b720304aa4fb9043e8d646d31d1d5fc15732e140105a122464f0117", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d36ec567a726e348992dacaa8d943e1c45179f9b942f8d2c7fc77b2337feae64", "generation_seconds_batch": 19.928565299953334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.387676954269409, "target_z": 4.156250349235283, "ce": 5.422942161560059, "genuineness": 3.823258876800537, "identity": 0.5341775417327881, "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_Triumph/4bd24f421b720304aa4fb9043e8d646d31d1d5fc15732e140105a122464f0117.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "4c94c2687efbf39604a8446a90d5346036464d4febbb63bfeb36654ea4bdce50", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a89e0647ebefcd34238781ded457147896e9fc6572415fdff2fd5a82e39ee58c", "generation_seconds_batch": 17.33960297401063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8036283254623413, "target_z": 1.1562500105828875, "ce": 6.268836498260498, "genuineness": 4.168440818786621, "identity": 0.549983024597168, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4c94c2687efbf39604a8446a90d5346036464d4febbb63bfeb36654ea4bdce50.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "4cc89022f85934f4fd7aa6f69e3d286400336b32d8619baf1918e34aee59d4a5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e30618b119ea27a157dfa86b880227a6def854e1a356b1ff61387c92584da852", "generation_seconds_batch": 22.66643609001767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9273821115493774, "target_z": 1.3906250123467019, "ce": 5.9431867599487305, "genuineness": 3.9299514293670654, "identity": 0.5311492681503296, "hypothesis": "I found the little box! It was beside the old window! We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4cc89022f85934f4fd7aa6f69e3d286400336b32d8619baf1918e34aee59d4a5.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "4ce48f4fa5017ab2c2c69fed312fff5b693fac5b52037a6f53a4dcb823c9ef36", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "61764ca262fdf468708db1eea7ce3202e34b0e90da5ae2fb05a1f037abfe2f70", "generation_seconds_batch": 19.721552208065987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.767188549041748, "target_z": 4.87500032454188, "ce": 6.38797664642334, "genuineness": 3.9173994064331055, "identity": 0.33886027336120605, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4ce48f4fa5017ab2c2c69fed312fff5b693fac5b52037a6f53a4dcb823c9ef36.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "4d692a5d88b39c30b6fc6c7795ffcdf41cde46623b0171252a1bf6e82812abc0", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f9a52d232640a6ec692f483b2894619b076cb09533004275384b9aba19dc67cd", "generation_seconds_batch": 21.4669050819939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47361820936203003, "target_z": 0.5312499682513379, "ce": 6.348263263702393, "genuineness": 4.362998008728027, "identity": 0.36353087425231934, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4d692a5d88b39c30b6fc6c7795ffcdf41cde46623b0171252a1bf6e82812abc0.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "4d981bb07d5beff134caa81d820fe90f150138e178822c9b29cef4cfd7670eb5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e5e6f4972162a38055be7bbe7bf3fbeb23972d7f903c4589eaffc9f9e6f569f3", "generation_seconds_batch": 23.213921567075886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5757131576538086, "target_z": 6.406250095245986, "ce": 5.387199878692627, "genuineness": 3.7416701316833496, "identity": 0.4387575387954712, "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_Triumph/4d981bb07d5beff134caa81d820fe90f150138e178822c9b29cef4cfd7670eb5.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "4d9f9a529c01ff912c52156b22e2392a7ac0291d8d9b2eda37f4505d2e622d53", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ecef2f227bb021a5f6fda4285a37cdb90ab287467d19f8639669280fdf2b87bb", "generation_seconds_batch": 15.65307938796468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.486679792404175, "target_z": 4.3437499894171125, "ce": 6.1020402908325195, "genuineness": 4.231201171875, "identity": 0.40679091215133667, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4d9f9a529c01ff912c52156b22e2392a7ac0291d8d9b2eda37f4505d2e622d53.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "4e4227a5c33e5c1d9bed38c0d084e07ec2a17ef97edd5110012319f0c345248f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "40f3ecd7d61bf1b582bb3eeaea672cbba072936601bffa54860a94d827d59dc9", "generation_seconds_batch": 14.470958753023297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.744157075881958, "target_z": 2.937499978834225, "ce": 5.863759994506836, "genuineness": 4.042920112609863, "identity": 0.27999982237815857, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4e4227a5c33e5c1d9bed38c0d084e07ec2a17ef97edd5110012319f0c345248f.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "4efbaed6936f0a8d23e826e2a4cb50fdc070a04d7d1f1dc381820701342a98f8", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2f5df7e94761cb67301d694c07010c7a2b8a6fceb0bde68e075d536a2e4f12bd", "generation_seconds_batch": 19.2490439619869, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15417876839637756, "target_z": -0.07373046836416557, "ce": 6.268836498260498, "genuineness": 4.262581825256348, "identity": 0.4611431956291199, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4efbaed6936f0a8d23e826e2a4cb50fdc070a04d7d1f1dc381820701342a98f8.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "4efd494883a1da1006daead2658c3c1c56653caeec9f14ccf32d8d833ab8c7bc", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e36bcc6cd3b995ddd546d8fcbbfafb2ee1cc953f495f92f1c0470f19b9392a35", "generation_seconds_batch": 19.607583576929756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1469597965478897, "target_z": -0.08740234534845695, "ce": 6.109982967376709, "genuineness": 4.432034492492676, "identity": 0.6151498556137085, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4efd494883a1da1006daead2658c3c1c56653caeec9f14ccf32d8d833ab8c7bc.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": "4f60df9e53bf4172758de55427d018706f5e5ee88f3e7d0375227e4a37d26c3f", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd6ed0cbb48ea32e2c6b38dae075bac0a5e327e0fe8cd935e65c67109c225866", "generation_seconds_batch": 20.655239825951867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23900167644023895, "target_z": 0.08691406503548343, "ce": 6.1894097328186035, "genuineness": 4.268857479095459, "identity": 0.5694177150726318, "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_Triumph/4f60df9e53bf4172758de55427d018706f5e5ee88f3e7d0375227e4a37d26c3f.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "4f88cba90a9d8bb82f1f92c4117233ad95e33895934cac601d52a64586e09d17", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9c71805987cb869db99bab249ff44521c2080423bf89d0e69abf2edca97ba585", "generation_seconds_batch": 22.380948810954578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9486939907073975, "target_z": 5.218750116411761, "ce": 5.506340026855469, "genuineness": 3.8671910762786865, "identity": 0.42748987674713135, "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_Triumph/4f88cba90a9d8bb82f1f92c4117233ad95e33895934cac601d52a64586e09d17.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": "4f9400275f1b54a2831192f796630e7c3b33b6cb420f030665aa58a96e7db782", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a773a6fdf64b46c19cffcf8b81cf0cb7c70a685945ed51622d2c90bd0cc5b35e", "generation_seconds_batch": 15.10113669000566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.80018949508667, "target_z": 4.93750020460249, "ce": 5.736677646636963, "genuineness": 4.049196243286133, "identity": 0.391878604888916, "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_Triumph/4f9400275f1b54a2831192f796630e7c3b33b6cb420f030665aa58a96e7db782.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "4fa306683f0750c43ec5a687977ae1ddf54307d6089d9066b020492737c44192", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "48aa56f26f23446a6ba30eb85aae5f64e4d32c7e7f12318c0f48c94baf64c8b5", "generation_seconds_batch": 15.02564369305037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7029057741165161, "target_z": 2.859374902990199, "ce": 6.308549880981445, "genuineness": 4.243753433227539, "identity": 0.38223087787628174, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4fa306683f0750c43ec5a687977ae1ddf54307d6089d9066b020492737c44192.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "4ff275d3431053cc4da29faed7fe20fb789c4769d32431ba3798e135da1d9b79", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4760d6ffb8aad64cd9ec15501860c4cff3b9933eb00950751a990d543b988529", "generation_seconds_batch": 21.526760459062643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1154184341430664, "target_z": 3.640624984125669, "ce": 5.816103935241699, "genuineness": 4.105680465698242, "identity": 0.19849301874637604, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4ff275d3431053cc4da29faed7fe20fb789c4769d32431ba3798e135da1d9b79.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "4ff99772ffbabcbb4b178ba07542ae00c6afdb10571aa8ac3196406521d14a51", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b8d17541b4727a1ffc51e9b7e167b54933de2662034458618bf6a67384340161", "generation_seconds_batch": 22.779245444922708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1295132637023926, "target_z": 1.7734374550227288, "ce": 6.09409761428833, "genuineness": 4.413206577301025, "identity": 0.6832273006439209, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/4ff99772ffbabcbb4b178ba07542ae00c6afdb10571aa8ac3196406521d14a51.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "501ed328067726983738b7477305f5b7c90126ca6b29d25b593faa5d819350f2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "814b3cd430430a4470e7819cbedffabf9aa2a6318db3fcd1b6ba072efeb552af", "generation_seconds_batch": 20.80737048201263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1814205646514893, "target_z": 3.7656251957834166, "ce": 5.808161735534668, "genuineness": 4.068024158477783, "identity": 0.5665761232376099, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/501ed328067726983738b7477305f5b7c90126ca6b29d25b593faa5d819350f2.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "50569a0e953724234c5c8d2ead91ca36925d42a5a0422a6ab100bf3ae179ec1f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f9ab11090e3847578c0af61e0ee0f27ae96e6fe7745a3d732fa47b18bcc990c9", "generation_seconds_batch": 21.574778396985494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20084425806999207, "target_z": 0.01464843761023841, "ce": 6.046441555023193, "genuineness": 4.300237655639648, "identity": 0.6068536043167114, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/50569a0e953724234c5c8d2ead91ca36925d42a5a0422a6ab100bf3ae179ec1f.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": "50652a2c9a911d6e4e1d71c7c9b7dedc547e8f5265acc98de1429f65f744277a", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "09f0f0f658edc7b289bad69e82aa5ebce8c3d9bb4c1f3482c312998733126585", "generation_seconds_batch": 16.597467512008734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23307180404663086, "target_z": 0.07568358961605962, "ce": 6.23706579208374, "genuineness": 3.9801597595214844, "identity": 0.33118170499801636, "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_Triumph/50652a2c9a911d6e4e1d71c7c9b7dedc547e8f5265acc98de1429f65f744277a.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "50bf73c4582b2ae0bd46def063e150c45a2a96775992b95e17a26b6aaf5811eb", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "de16da0ab26da63b6743d96beecc03afec8c3d1dbd8509ba0ffc70f3439504ed", "generation_seconds_batch": 16.156458932091482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8778805732727051, "target_z": 1.2968749664875232, "ce": 5.959072113037109, "genuineness": 4.080576419830322, "identity": 0.42391443252563477, "hypothesis": "I found the little box! It was beside the old Wingen, the conside together.", "wer": 0.3125, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/50bf73c4582b2ae0bd46def063e150c45a2a96775992b95e17a26b6aaf5811eb.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "50fd2d97b4e8c92c259bd2318e18337fe3fb15a2b02e373ad9636d7144f6f11a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ae715c7b7a2c5f3136af415633c3675ec725d961cb362342cc4e68214cf965a", "generation_seconds_batch": 16.888750085025094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5709017515182495, "target_z": 2.609374931211232, "ce": 6.1894097328186035, "genuineness": 4.356721878051758, "identity": 0.5340924859046936, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/50fd2d97b4e8c92c259bd2318e18337fe3fb15a2b02e373ad9636d7144f6f11a.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "51481c0a4d9e2bbfee02455ba6f8599aaffb46e23982c02dff7ed9741f943e1b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0c921129bbedd5c22d2870c806a42a671fd3e3599624e0d3106ca61d100e0b6d", "generation_seconds_batch": 19.874887967016548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1652650386095047, "target_z": -0.05273438668527148, "ce": 6.24500846862793, "genuineness": 4.243753433227539, "identity": 0.2537991404533386, "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_Triumph/51481c0a4d9e2bbfee02455ba6f8599aaffb46e23982c02dff7ed9741f943e1b.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "51685661d8ab9713c13fba6c8c7eab280b6c92851331bfae553207655484c6e0", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e2fb4884f369b52456eb34933adc827c1a730402552c8ba67de4a5ceccb67ea0", "generation_seconds_batch": 15.015535069047473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.151858389377594, "target_z": -0.07812499118092718, "ce": 6.372091293334961, "genuineness": 4.419482707977295, "identity": 0.2760477662086487, "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_Triumph/51685661d8ab9713c13fba6c8c7eab280b6c92851331bfae553207655484c6e0.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "51a47890c7669a0ef31108c5779aa2d8a97a663c80795dab29a98ca4e421efc7", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9d882d21127541fe848f0956933048bc834f4c29772a728bf8294ab12021d5cc", "generation_seconds_batch": 21.90100623096805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2986434698104858, "target_z": 2.0937500176381456, "ce": 5.728734970092773, "genuineness": 4.105680465698242, "identity": 0.5648651123046875, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/51a47890c7669a0ef31108c5779aa2d8a97a663c80795dab29a98ca4e421efc7.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "5222f564ea2f63f3bdf1b0364592d6fcd316893c8afc91de46e7ada1ade039ca", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cb99f152b9bf1847396f175c4ad70eae5fe39de02b0a088591b0a4afdd577519", "generation_seconds_batch": 19.390129649895243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0858563631772995, "target_z": -0.2031250052914437, "ce": 6.149696350097656, "genuineness": 3.798154592514038, "identity": 0.38654977083206177, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5222f564ea2f63f3bdf1b0364592d6fcd316893c8afc91de46e7ada1ade039ca.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "522bfe26539e58be5efcd327845028131eba6558fcecab7f82d62bdc2f263713", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fca7ecfa23c8246e2b122a989157a304cdd7897e2998f5df4131b0014fed8061", "generation_seconds_batch": 14.737742029014044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31480085849761963, "target_z": 0.23046873103899346, "ce": 5.617537498474121, "genuineness": 4.168440818786621, "identity": 0.6544832587242126, "hypothesis": "La porte est encore ouverte ! J'ai posé ton manteau sur la chaise ! Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/522bfe26539e58be5efcd327845028131eba6558fcecab7f82d62bdc2f263713.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": "529b9e0455fc73aaa965795a79e389dc00916537ee635d5f3ec96f6a54f62b1e", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The road turns left behind the bridge.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "287ca144b2d57f073aa4a72606548cc95460613d1173febec9df331b2a00a3b1", "generation_seconds_batch": 19.515399668947794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06523074209690094, "target_z": -0.2421874867713908, "ce": 6.435632705688477, "genuineness": 3.9048471450805664, "identity": 0.2977364659309387, "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_Triumph/529b9e0455fc73aaa965795a79e389dc00916537ee635d5f3ec96f6a54f62b1e.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "530b73c32e16a69d55fca6fc822e82f2ec7125e76271e482c2653ec98a8e345f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "27faa111dd4c6bb896e6a4e6ae50e82c7deffd3a1e3d0873aa2a80bc7ca40cb9", "generation_seconds_batch": 19.26809847599361, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14567069709300995, "target_z": -0.08984374691332452, "ce": 6.054384231567383, "genuineness": 4.494794845581055, "identity": 0.557328999042511, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/530b73c32e16a69d55fca6fc822e82f2ec7125e76271e482c2653ec98a8e345f.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "535d344f19c010c074fd24e742964d9418d14e17f776cf08a543f2d092247cf4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e54b85a496bcc88d0e5b5370c368ac8766e9c0e836d2d9843a178112171701a5", "generation_seconds_batch": 19.67476446600631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.62418532371521, "target_z": 0.8164062354485299, "ce": 6.268836498260498, "genuineness": 4.425758361816406, "identity": 0.4736756682395935, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/535d344f19c010c074fd24e742964d9418d14e17f776cf08a543f2d092247cf4.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "53ca09a9c5fe4c54ce212417f8425add1da62c31e5c544444adbee6d3a5a94bb", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ba2bb12b28e36849cf928d478f99db8bcf30240872b78ae724546155ba5db376", "generation_seconds_batch": 19.348604814964347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5148695111274719, "target_z": 0.609375044095364, "ce": 6.229123115539551, "genuineness": 4.262581825256348, "identity": 0.4072476625442505, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/53ca09a9c5fe4c54ce212417f8425add1da62c31e5c544444adbee6d3a5a94bb.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "53eb07d2d67f064483602cc5425656eb975f9720faf73b1b4cad5b6b1a9ed2e5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0c2ef0d028897e5246ad53b51c198882de82a4fe081be21fec95c290a139be58", "generation_seconds_batch": 16.323977001942694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1047625541687012, "target_z": 1.7265625449772712, "ce": 6.300607204437256, "genuineness": 4.381826400756836, "identity": 0.3713029623031616, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/53eb07d2d67f064483602cc5425656eb975f9720faf73b1b4cad5b6b1a9ed2e5.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "540960ae74e7e154f1b55a52b989274af946a137e53622aa599112fc589fd2f5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4e7785ffe6240ef37f38a137b878e87e3165ae53cb293153c454205c6da31eff", "generation_seconds_batch": 21.951821477035992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.075886607170105, "target_z": 1.6718749241559738, "ce": 6.149696350097656, "genuineness": 4.432034492492676, "identity": 0.6026861071586609, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/540960ae74e7e154f1b55a52b989274af946a137e53622aa599112fc589fd2f5.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "7676f0d7e16156336c6c88e71b6958a4cf28ac6dbb7133811a769aac9ede29dc", "generation_seconds_batch": 16.15537664690055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41174131631851196, "target_z": 0.4140624673694306, "ce": 6.324435234069824, "genuineness": 4.080576419830322, "identity": 0.5192272663116455, "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_Triumph/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "54ae26faf9ddfd137215838018abc6a9cd5acbaf173bb2dcb6a1c9b5a8e40518", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c015cd609df570ff74015daba49858206f5e8e68a2e489b7ee78a6155c3c49dd", "generation_seconds_batch": 19.227986532030627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3663649559020996, "target_z": 0.3281250194019602, "ce": 6.3641486167907715, "genuineness": 4.011539936065674, "identity": 0.3650113344192505, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/54ae26faf9ddfd137215838018abc6a9cd5acbaf173bb2dcb6a1c9b5a8e40518.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "5539fae9034e198015d3b14f9747283dd56e93d7c58df457704308be0b550c83", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fb16c0cdb244cdfa18b02d056884914cee2489975dd521225973d4d6b03047c1", "generation_seconds_batch": 19.698863492929377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26323679089546204, "target_z": 0.13281249911809273, "ce": 6.125868320465088, "genuineness": 4.262581825256348, "identity": 0.7792510390281677, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5539fae9034e198015d3b14f9747283dd56e93d7c58df457704308be0b550c83.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "553e94c3bebd001abcd64fd4e09d109b0ff51212cf6e65659709521af9202e9b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fbd2dcb306404228c496f6d78cd9d3658613d9a73a5a87cfe769435c4d759087", "generation_seconds_batch": 21.05507771705743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21502438187599182, "target_z": 0.04150391126584766, "ce": 6.372091293334961, "genuineness": 4.557555198669434, "identity": 0.507433295249939, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/553e94c3bebd001abcd64fd4e09d109b0ff51212cf6e65659709521af9202e9b.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "55d36317691c585db3433f3566cbeb57871a772e077f30b8a7d863e996229704", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d2edef61610ca589af550f1c8e90e3293ce1d5ac3bbfe9d2e5966e828bc727da", "generation_seconds_batch": 23.37577424303163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1384517252445221, "target_z": -0.1035156238976159, "ce": 6.213237762451172, "genuineness": 4.532451152801514, "identity": 0.6710981130599976, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/55d36317691c585db3433f3566cbeb57871a772e077f30b8a7d863e996229704.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "5668cf3de0647130cb931eb512cbe259bd8f51ed81fdfd456054d429f85c3a5c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3e39f9048666eb967a2e4249126cc4974e744351b5e5858ea513d8997f7a9db2", "generation_seconds_batch": 21.08815476996824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17944516241550446, "target_z": -0.025878913029662224, "ce": 6.2767791748046875, "genuineness": 4.218649387359619, "identity": 0.6204534769058228, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5668cf3de0647130cb931eb512cbe259bd8f51ed81fdfd456054d429f85c3a5c.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "566ecec6c7a615c40825b10f6c07421632f5efccc95139ab05bc2e8c697639ef", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "74dc20f0fe6eaa4ab865b2e167ec69e3ff93d647891047cb73cfa4ecdb1c266c", "generation_seconds_batch": 20.17424093594309, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3563952445983887, "target_z": 2.203125033512477, "ce": 6.006728172302246, "genuineness": 4.400654315948486, "identity": 0.6354188919067383, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/566ecec6c7a615c40825b10f6c07421632f5efccc95139ab05bc2e8c697639ef.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "56e3cffa77bb9acc7408cd4a7bd9595250927a8f071c2044aecae40b7cac9c1c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "285ce4989e02fb0ec97a2612059f005bc12fd9bdc99b08965ea1309f2806f681", "generation_seconds_batch": 14.846591594978236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.443709135055542, "target_z": 6.15625012346702, "ce": 6.062326908111572, "genuineness": 4.036643981933594, "identity": 0.2836960256099701, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/56e3cffa77bb9acc7408cd4a7bd9595250927a8f071c2044aecae40b7cac9c1c.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "5786c70dd864d2e0f1afb2a99291819dd1ba901d276585106e12259bfdefdbf7", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4a8052662f7d8b2800289bd88342183f78cf2eded9eee69939ac747a99d5721f", "generation_seconds_batch": 20.046443048049696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.494243860244751, "target_z": 0.5703125061733509, "ce": 6.157639026641846, "genuineness": 4.419482707977295, "identity": 0.6966050863265991, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5786c70dd864d2e0f1afb2a99291819dd1ba901d276585106e12259bfdefdbf7.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "579b6dcfb48989b8f05d4076f4ef181bcfa33b94fe29940e56948e3b59c6abaf", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4910f27a82bd6705d63b0d2c94ac5141f8e88686697e5b3dac46cd2e1a3935bc", "generation_seconds_batch": 19.4689677299466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.470179319381714, "target_z": 4.3125000493868075, "ce": 5.569881439208984, "genuineness": 3.9425034523010254, "identity": 0.20783835649490356, "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_Triumph/579b6dcfb48989b8f05d4076f4ef181bcfa33b94fe29940e56948e3b59c6abaf.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": "5889745eb02f342b14de58dbe7e57e0e0e915492f454902c78977d7e7a834f9d", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a48784f8f6359d7e34c289596053e80b45fed62384e2d2f7b91f901817859bb", "generation_seconds_batch": 18.101943789981306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16810107231140137, "target_z": -0.04736327502152982, "ce": 6.1894097328186035, "genuineness": 4.545003414154053, "identity": 0.680942177772522, "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_Triumph/5889745eb02f342b14de58dbe7e57e0e0e915492f454902c78977d7e7a834f9d.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "5894a6804b171945dc5c39fa97a6c07ce6132b0c087fecdc803c3069467caadb", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d49f5251f0f51e1824557f0ed3efb012993bf7df3f0de2d792ad4ca391412f87", "generation_seconds_batch": 21.155647889943793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.296924114227295, "target_z": 3.9843752275320785, "ce": 6.23706579208374, "genuineness": 3.8546390533447266, "identity": 0.4223979115486145, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5894a6804b171945dc5c39fa97a6c07ce6132b0c087fecdc803c3069467caadb.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "591a3fd7a482a51e36e661d5136ba5bbabcbd8f88051197064e539333dda5ef6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5032e3c8b35afa6ddbd15b8a6fe63e9a14fa8c4bf6b0cd12c68adcb2a352940f", "generation_seconds_batch": 21.27039734099526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15082710981369019, "target_z": -0.08007811243282124, "ce": 6.292664527893066, "genuineness": 4.243753433227539, "identity": 0.3745015859603882, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Dis-moi quand tu es prêt.", "wer": 0.3333333333333333, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/591a3fd7a482a51e36e661d5136ba5bbabcbd8f88051197064e539333dda5ef6.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": "596d29175745644f29c09801a6b960e839b9bf7eb4f9d581246dbacdc9f5c1b1", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a8d9505eadd0508829c7420b3ed9242abdebbe559a6b88d07c2fdae4dfb9dc5", "generation_seconds_batch": 20.655239825951867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15469440817832947, "target_z": -0.07275390773821853, "ce": 6.197352409362793, "genuineness": 4.369274139404297, "identity": 0.5976314544677734, "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_Triumph/596d29175745644f29c09801a6b960e839b9bf7eb4f9d581246dbacdc9f5c1b1.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "59a3bd5d7e7ef92891cd5b4c227f3a6962cb525acf3222ec83cdc787dd469b68", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6fb7f6f841ab8b2bcb1625942048d8e35d06dce16c552384c566ef277394f9e7", "generation_seconds_batch": 21.51909775810782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.750688076019287, "target_z": 4.843750384511575, "ce": 5.6413655281066895, "genuineness": 3.9676074981689453, "identity": 0.5906618237495422, "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_Triumph/59a3bd5d7e7ef92891cd5b4c227f3a6962cb525acf3222ec83cdc787dd469b68.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "5a0eb77a18a571f5374ffebee6274208cb22fa9d4b35adc361ea306996d1a04a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3c53ec842ea96f34b7593db5c8aaf72d70235da4c8700b9a75ebb26d2042e6ee", "generation_seconds_batch": 22.396641165949404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6963750123977661, "target_z": 0.9531249488493777, "ce": 5.7684478759765625, "genuineness": 3.986435890197754, "identity": 0.4471445679664612, "hypothesis": "Uh I found the little box! It was beside the old window! We can look inside together!", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5a0eb77a18a571f5374ffebee6274208cb22fa9d4b35adc361ea306996d1a04a.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "5a3106d0255c5bcb6dd0d48bc2ad72a1f90cbfd3c58aff53684629cfffe3f902", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6cc445b047ce322d8413670ba4aa8ebddb04e778e8279855dc1f9009ec1d339c", "generation_seconds_batch": 17.549793955986388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9504133462905884, "target_z": 3.328124906517828, "ce": 5.609594821929932, "genuineness": 3.948779582977295, "identity": 0.376894474029541, "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_Triumph/5a3106d0255c5bcb6dd0d48bc2ad72a1f90cbfd3c58aff53684629cfffe3f902.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "5a4cdbabcfd73cb1198c393b3439be20d9e305971c57910574a6e5b955f9e997", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "86471235432adeac3a7904499dcadad92e0b2afd322722e4e43002261b2ec801", "generation_seconds_batch": 21.241924621979706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7936586141586304, "target_z": 3.0312500246934038, "ce": 6.054384231567383, "genuineness": 4.287685871124268, "identity": 0.639697790145874, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5a4cdbabcfd73cb1198c393b3439be20d9e305971c57910574a6e5b955f9e997.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": "5b3ff32cf07d12146bf23742f1ad83a00a50e27696212b2b5a86ae54da419ed5", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cf48f72c62bbf79fae9abc22cd0ca2e9a52110023e4978c3ed395b285a68ca68", "generation_seconds_batch": 19.989831845043227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11885737627744675, "target_z": -0.14062499823618543, "ce": 6.348263263702393, "genuineness": 4.833701133728027, "identity": 0.6002737283706665, "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_Triumph/5b3ff32cf07d12146bf23742f1ad83a00a50e27696212b2b5a86ae54da419ed5.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "5b942e695eee1934bd1661c1e2d656af5b1a92db205018757cdde56cf2d86564", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b7a3d26fa873e343c8722e28dadfb2772e1f0f4e6d9c6ec56c08845cd266155b", "generation_seconds_batch": 23.373311821953394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2699401378631592, "target_z": 0.14550784369747008, "ce": 6.046441555023193, "genuineness": 4.068024158477783, "identity": 0.24800193309783936, "hypothesis": "De deur 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_Triumph/5b942e695eee1934bd1661c1e2d656af5b1a92db205018757cdde56cf2d86564.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "5bb70cb4ef1eece87b9a99fa44c4b1e8d35ae9ed2ddfa806398618aea161b500", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "48de347c03e01ce81f328e4aeceed5482b2711394a18aeb711251a121ee17200", "generation_seconds_batch": 14.793119069072418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4437110424041748, "target_z": 0.4746093390622783, "ce": 6.133810997009277, "genuineness": 4.482243061065674, "identity": 0.4886890649795532, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5bb70cb4ef1eece87b9a99fa44c4b1e8d35ae9ed2ddfa806398618aea161b500.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "5bdcca28550c28b7c09207036e67ddc34528ec9cabf8c7fce293e561b74d827f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "362c127ca6fb13aad7f27ace7a05ccfe35426c008090f772a81c2bb1bde541f1", "generation_seconds_batch": 19.904625035007484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9645082354545593, "target_z": 1.46093749029902, "ce": 6.173524379730225, "genuineness": 4.375550270080566, "identity": 0.6327317953109741, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5bdcca28550c28b7c09207036e67ddc34528ec9cabf8c7fce293e561b74d827f.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "5c240b2bf87fe41b9fa9c581a48fcb85c0111ade69ba90657983f87410fa3234", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "200ddde29c241d0abcae3a3382730b3c328ff1c57fccd013ebd2890e5b8cb196", "generation_seconds_batch": 22.779245444922708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1872650384902954, "target_z": 1.8828124708970597, "ce": 5.959072113037109, "genuineness": 4.293961524963379, "identity": 0.6241123676300049, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5c240b2bf87fe41b9fa9c581a48fcb85c0111ade69ba90657983f87410fa3234.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": "5c6ec4b6cac27b0beefc9c1dd1cc07819aa721edaf0c4ccb1e22ab68a49755e4", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e3b6fa85d8f78f9dc9cd7b6cee404902bf7be3f756b39910c9870a0e36477fcc", "generation_seconds_batch": 20.141228755936027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1727418303489685, "target_z": -0.03857422938800658, "ce": 6.229123115539551, "genuineness": 4.406930446624756, "identity": 0.5746740102767944, "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_Triumph/5c6ec4b6cac27b0beefc9c1dd1cc07819aa721edaf0c4ccb1e22ab68a49755e4.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "5c70e369c6c8fc6af8b9bcc966422afb28a9dbf57f09e528a215ad915da8b4bf", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e9c5996cc8a5d219b3044028930dceb45ac75ec5dcfba11f47ed8750dc6ac5f3", "generation_seconds_batch": 20.898307967931032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6014971137046814, "target_z": 0.7734374550227286, "ce": 6.070269584655762, "genuineness": 4.193545341491699, "identity": 0.6670604944229126, "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_Triumph/5c70e369c6c8fc6af8b9bcc966422afb28a9dbf57f09e528a215ad915da8b4bf.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": "5ca6df3c0e645384a60ef1173721f5a08108ad31d4a482e2c068c1feae162de1", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2f4f4ca17b775d31d8ddd3096465537d024b6fc326474c7be5410a544305d35", "generation_seconds_batch": 18.86962231202051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10648199915885925, "target_z": -0.1640624955904636, "ce": 6.24500846862793, "genuineness": 4.281409740447998, "identity": 0.6119331121444702, "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_Triumph/5ca6df3c0e645384a60ef1173721f5a08108ad31d4a482e2c068c1feae162de1.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "5cf568d36d7b7845b98044b9ccf1d948f8b6256fb02afe79a8a37815bf4ee405", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d7af6cf1c8d1ac99b74b45a813efe0e1913c893c3d7129a194814066a0e0b34c", "generation_seconds_batch": 19.467257536947727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16990581154823303, "target_z": -0.04394531283071523, "ce": 5.7247633934021, "genuineness": 3.537698984146118, "identity": 0.527634859085083, "hypothesis": "De deur staat nog open! Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5cf568d36d7b7845b98044b9ccf1d948f8b6256fb02afe79a8a37815bf4ee405.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "5d2cade1a7b30aae5f8877f2aa21a09ca764f7dd1e68fbc876ad3e2b0e5383d8", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5443836c01610ccef5467e0a94b82b7e04622fb700578bb9d724645063d68c0f", "generation_seconds_batch": 21.43845537607558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.41070818901062, "target_z": 6.09375024340641, "ce": 5.732706069946289, "genuineness": 3.9676074981689453, "identity": 0.2758827209472656, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5d2cade1a7b30aae5f8877f2aa21a09ca764f7dd1e68fbc876ad3e2b0e5383d8.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "5d749054ea5ba7c2b104793dcb7903b86102e684fbaf08c917a41897aa967873", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5e3b4faa9767ad7d9961f05f44e2fafc9d27e2127886cbcc00c2b2e4f9e70562", "generation_seconds_batch": 16.562565749976784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4014285206794739, "target_z": 0.39453125485049007, "ce": 6.205295085906982, "genuineness": 4.356721878051758, "identity": 0.5927226543426514, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5d749054ea5ba7c2b104793dcb7903b86102e684fbaf08c917a41897aa967873.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "5d83ea9adc550fcd7667466e710d0427a3e79fb5ff1ead82d21b8e3638e1ca2d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c1876119bae2e6e13ad9ff5f59c374f24b249f8f1d4815c9148a6afbaf248327", "generation_seconds_batch": 21.155647889943793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.526211738586426, "target_z": 6.312500275155072, "ce": 6.221180438995361, "genuineness": 3.9801597595214844, "identity": 0.14242148399353027, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5d83ea9adc550fcd7667466e710d0427a3e79fb5ff1ead82d21b8e3638e1ca2d.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": "5d9ef23c2a8cb525e85d4d91c4a59d6d7a15138a80702f61d8cdc75f8c45fab9", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb2f8fc30d7d5aec9dbebfa6ea4a3c16efc95e1ff3ce65a1a7db0c0581e9bceb", "generation_seconds_batch": 18.164747253991663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07760611176490784, "target_z": -0.21875000352762913, "ce": 6.181467056274414, "genuineness": 4.293961524963379, "identity": 0.5740615129470825, "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_Triumph/5d9ef23c2a8cb525e85d4d91c4a59d6d7a15138a80702f61d8cdc75f8c45fab9.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "b3cd4e036174b299f0a3ba5516a1c46322165d6a9f85fe23bcaf4861f2c861f9", "generation_seconds_batch": 15.022641762974672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04254254698753357, "target_z": -0.285156238976159, "ce": 6.133810997009277, "genuineness": 4.344170093536377, "identity": 0.7607215642929077, "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_Triumph/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "5e538b6c9f30d30d7f64ada9024946b51e4ecf48ac5cc83cf39a87cd31a609ce", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "05afe01e9af1b0d32bdf9ac8060522749a4e611d11e8fb91cec30f9f92738562", "generation_seconds_batch": 16.624027723097242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2531817853450775, "target_z": 0.11376951047005969, "ce": 6.038498878479004, "genuineness": 3.8671910762786865, "identity": 0.4437987208366394, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5e538b6c9f30d30d7f64ada9024946b51e4ecf48ac5cc83cf39a87cd31a609ce.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "5e687de6925f131bdf15d761caf20b90e136f8705c987aa518277ec4a39a409a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f0cc5d5148c64a4df52e951372b22cae6c3f7afa540f64daf31ea2de2855969b", "generation_seconds_batch": 19.25428751099389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5231197476387024, "target_z": 0.6250000141105165, "ce": 6.419747352600098, "genuineness": 4.243753433227539, "identity": 0.42240867018699646, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5e687de6925f131bdf15d761caf20b90e136f8705c987aa518277ec4a39a409a.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "5ed3fb440842b0e8ce94b32474deb797e39d58d4db97b02ee4f3bb90ee5bbbcc", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cc1aa13553cc703d895cd1676f81a7a0367834444eac965837fd7f38fc0626a3", "generation_seconds_batch": 19.333409009967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33233267068862915, "target_z": 0.2636719052053244, "ce": 5.95112943649292, "genuineness": 4.080576419830322, "identity": 0.5298951864242554, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5ed3fb440842b0e8ce94b32474deb797e39d58d4db97b02ee4f3bb90ee5bbbcc.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "5ed9ec0fe96449dea0087de85fa760ec00a4244cd8ec2556d31b7a0773a33dab", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d69835ad98ddfa153deb16fd3f19e5cff4489126bda3f76ff192567471eb4b48", "generation_seconds_batch": 21.47745174402371, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23951731622219086, "target_z": 0.08789062566143047, "ce": 6.316492557525635, "genuineness": 4.406930446624756, "identity": 0.556493878364563, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5ed9ec0fe96449dea0087de85fa760ec00a4244cd8ec2556d31b7a0773a33dab.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "5f0612ede0b83f1a8507e805c7d2c2fffedaa42e41f81ec303a595fb588cb799", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b403e5481f57ada3b44be1f65a7b7ca7a7f00591e659fdad0795e383e03c9dc9", "generation_seconds_batch": 20.17424093594309, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6695617437362671, "target_z": 0.9023437963001323, "ce": 6.340320587158203, "genuineness": 4.519899368286133, "identity": 0.7023820877075195, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5f0612ede0b83f1a8507e805c7d2c2fffedaa42e41f81ec303a595fb588cb799.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "5f1774d6cb52dc08744dbf4ee94d8996d8382139844587f7ca16383b98936707", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d4d5e0c3f6d026b27ad9927817e6cdaadc74f73844493e6decd528d7d363309b", "generation_seconds_batch": 19.298058331012726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6571863293647766, "target_z": 0.8789062283932716, "ce": 6.213237762451172, "genuineness": 4.331617832183838, "identity": 0.3336770534515381, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/5f1774d6cb52dc08744dbf4ee94d8996d8382139844587f7ca16383b98936707.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": "5f30c52f14a4f8b7cbf8e9679500df8008927c70b6a2b9c8cf125adb315aa9d3", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Your message arrived after I had left.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c0573c3dc18b59544251577a5d95db9465df4a41fa74b1b94500f30d23c27a2a", "generation_seconds_batch": 20.668166594929062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10493507236242294, "target_z": -0.16699219157882117, "ce": 6.292664527893066, "genuineness": 3.9173994064331055, "identity": 0.4178594946861267, "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_Triumph/5f30c52f14a4f8b7cbf8e9679500df8008927c70b6a2b9c8cf125adb315aa9d3.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "60acf8eab26c34872d3ecc37064c03cb33ebf6ff097593ebb7a825a1fba4d246", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3f75178a21b4d8c9d6c182b6663393b9129c3949d0c40f0286ce80c1539149eb", "generation_seconds_batch": 19.55016930110287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.884411334991455, "target_z": 3.2031249206283445, "ce": 6.4515180587768555, "genuineness": 4.243753433227539, "identity": 0.2655864953994751, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/60acf8eab26c34872d3ecc37064c03cb33ebf6ff097593ebb7a825a1fba4d246.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "60b23e7e6ff2b882f160641ad4d1af9c217b16f1d3c87d0fac40f54966cb7899", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b10f57d889c9bb8b3d2f48abf1a5671f1266fe9e359fae27889cf8c6d68ae613", "generation_seconds_batch": 21.430692394962534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6056222915649414, "target_z": 0.7812500529144368, "ce": 5.95112943649292, "genuineness": 4.005263805389404, "identity": 0.6006439924240112, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/60b23e7e6ff2b882f160641ad4d1af9c217b16f1d3c87d0fac40f54966cb7899.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "60b9b426cbc05a5b1af8f9f4f6f1fc6770fb55fee8ea8d01d13cefbcd5d84238", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ed8772f54615ae63d6c007fdcaa8b7cbdf08957b84dde8ebb0f8db282b7f47cf", "generation_seconds_batch": 24.07842190703377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5293074250221252, "target_z": 0.6367187416218808, "ce": 6.356205940246582, "genuineness": 4.293961524963379, "identity": 0.4032658338546753, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/60b9b426cbc05a5b1af8f9f4f6f1fc6770fb55fee8ea8d01d13cefbcd5d84238.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "619c46ee0f18c20186ea477592312d68a474949e44be734971cdd58a30388eae", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "affe0cdaebea06bd432d1cb98736eac8e9ed53a04d0b76a5893621fa860f52c6", "generation_seconds_batch": 16.88860701303929, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1603664606809616, "target_z": -0.06201171263176824, "ce": 6.038498878479004, "genuineness": 3.9048471450805664, "identity": 0.4546426236629486, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/619c46ee0f18c20186ea477592312d68a474949e44be734971cdd58a30388eae.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "61d627d6f3120bbc9ef4518a7d4ca17f98a9ad8cea9ba4511a6017c5375d19e4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f601ef14e7212122bc2b93d690dc82c9163c38e7c2c1349356836b9fbb5752f1", "generation_seconds_batch": 19.470512664993294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.059386134147644, "target_z": 1.640624984125669, "ce": 6.022613525390625, "genuineness": 4.118232727050781, "identity": 0.4824102818965912, "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_Triumph/61d627d6f3120bbc9ef4518a7d4ca17f98a9ad8cea9ba4511a6017c5375d19e4.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "6203ed2b151ee6cd39298c79ed18f24c133ad7e283c4ef3a3416cb323c27b6d4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5955564c64cf6d08ae00136b326d2c2e03e04fae56693a4c1e92a7ad1528c6ab", "generation_seconds_batch": 23.169209641986527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1649200916290283, "target_z": 3.7343752557531116, "ce": 5.903473377227783, "genuineness": 4.099404335021973, "identity": 0.5143798589706421, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6203ed2b151ee6cd39298c79ed18f24c133ad7e283c4ef3a3416cb323c27b6d4.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "62831c982d3a2ae53dd62e9e6093812386384cf47e2fb74b6a93415589d4b4d7", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2f81183871adf70d8ee7b5e19234263f7341f384e445bb4d7d3953e1145e0681", "generation_seconds_batch": 15.66636643698439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4199915826320648, "target_z": 0.42968749382664906, "ce": 6.300607204437256, "genuineness": 4.632867813110352, "identity": 0.672234833240509, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/62831c982d3a2ae53dd62e9e6093812386384cf47e2fb74b6a93415589d4b4d7.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "629742307590a0370f4e28637b2ac347c0fa0fb798963c2cb3259a8f91f7543c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7566d2370ab7d36aefc8256d1e96943edc307cd61d555b2b9a35b7faa3feffba", "generation_seconds_batch": 21.52521689608693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3921470046043396, "target_z": 0.37695316358344355, "ce": 6.2767791748046875, "genuineness": 4.369274139404297, "identity": 0.267473965883255, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/629742307590a0370f4e28637b2ac347c0fa0fb798963c2cb3259a8f91f7543c.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "62dafb77f1b3ba98e392eb6726bf6c13f7814f1333c72e511d6429e418928fc9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d847bfff76b447bf59027b1fd57c68ae6a510947a77d30f019df8c28391ad75e", "generation_seconds_batch": 19.395880938973278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.915006697177887, "target_z": 1.3671874444398413, "ce": 6.2767791748046875, "genuineness": 4.457139015197754, "identity": 0.6762063503265381, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/62dafb77f1b3ba98e392eb6726bf6c13f7814f1333c72e511d6429e418928fc9.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": "63cd05346af77cb6ae285d742a2827120ae1a3e67558a30d27b7e289f0539697", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f028f5a44cc221bf04c6539ff79034f73cf10417c4441c457188c903a9488c4c", "generation_seconds_batch": 21.588928558980115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2812842130661011, "target_z": 0.16699217746830466, "ce": 6.046441555023193, "genuineness": 4.20609712600708, "identity": 0.681147575378418, "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_Triumph/63cd05346af77cb6ae285d742a2827120ae1a3e67558a30d27b7e289f0539697.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": "63dc62b25c5ca8fa1490da3e11e1705e56a9770d3b530d5ed3ea24585cfd62a8", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e3510cb84179570cbc62d397af02c353e231dec4d952030150cfa61303de076e", "generation_seconds_batch": 14.991815250949003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9562579989433289, "target_z": 1.4453125202838675, "ce": 6.268836498260498, "genuineness": 3.911123275756836, "identity": 0.5937564373016357, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/63dc62b25c5ca8fa1490da3e11e1705e56a9770d3b530d5ed3ea24585cfd62a8.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": "64cf3b2535bbe36940cf7b0528dadec7dea836eb65349820149ec0e3e8698608", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c8c4b193eba940dfa64d965970ebde82ad68395273bd3231271f14e81d26f520", "generation_seconds_batch": 21.588928558980115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12813889980316162, "target_z": -0.12304689285862244, "ce": 6.078212261199951, "genuineness": 4.20609712600708, "identity": 0.49448809027671814, "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_Triumph/64cf3b2535bbe36940cf7b0528dadec7dea836eb65349820149ec0e3e8698608.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": "64dfec8ab3a64133c4b94986f9e15ba4a75fff85c6c015b18f6314deb47f56bf", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "44f4d8eb174d9322f1368fe749bbdd247cc14191ff2e79a22b8a5894ce98316d", "generation_seconds_batch": 14.781641172943637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0305103063583374, "target_z": 1.5859375890726355, "ce": 5.824047088623047, "genuineness": 4.055472373962402, "identity": 0.4753149151802063, "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_Triumph/64dfec8ab3a64133c4b94986f9e15ba4a75fff85c6c015b18f6314deb47f56bf.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "65103085574238cf0ae69a0ca8d1d06ef0bb886b530e868d82ada51c0794b625", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1c7841c3b4f79dfc966b6b56d91700fe23538927b076c607eda3ac0f908858be", "generation_seconds_batch": 19.298058331012726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7293760180473328, "target_z": 1.0156249417941194, "ce": 6.252951145172119, "genuineness": 4.444586753845215, "identity": 0.4154911935329437, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/65103085574238cf0ae69a0ca8d1d06ef0bb886b530e868d82ada51c0794b625.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "651241a8dce3ff45405fe4ee20adf414d22621ed2dfbba985d6f583fe70549d1", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c2b07ab3608ea40f78165d8155cd427e6797ef60ae6c5c339265278247e8ad12", "generation_seconds_batch": 15.811354993027635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8448795676231384, "target_z": 1.2343749735427816, "ce": 6.205295085906982, "genuineness": 4.293961524963379, "identity": 0.6253555417060852, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/651241a8dce3ff45405fe4ee20adf414d22621ed2dfbba985d6f583fe70549d1.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "6542c4bad0fb6219a97943747c68f76a5cf9f8b4eb5a9465c924e69d1a0962ed", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "350fd30d96252d91dba8d84a13ae302448010fa8d302c822f956a644dce73ec7", "generation_seconds_batch": 21.761646850965917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8596606254577637, "target_z": 3.1562500105828875, "ce": 5.998785495758057, "genuineness": 4.268857479095459, "identity": 0.10977190732955933, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6542c4bad0fb6219a97943747c68f76a5cf9f8b4eb5a9465c924e69d1a0962ed.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": "654301a1507d7fe4d43a83f003dc10d0c18baa01a0e8c602bd7e54efcfabd22c", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47e73bc53247e9e1d37395713ff05ee07d0e2b97fcf9649766d9af07b7ba517a", "generation_seconds_batch": 18.86962231202051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18692195415496826, "target_z": -0.011718755732397328, "ce": 6.348263263702393, "genuineness": 4.469690799713135, "identity": 0.5833203196525574, "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_Triumph/654301a1507d7fe4d43a83f003dc10d0c18baa01a0e8c602bd7e54efcfabd22c.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "65a08c1199a2314242110e8311459eefdfb9da1f7ee0deb84d1ed84de824e689", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fbbd4a2bae9b12d427f67563ce9dfbfdee8c55c171bc5278c2e4fdf86ce66471", "generation_seconds_batch": 20.330683349980973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5361814498901367, "target_z": 4.437500261044555, "ce": 6.062326908111572, "genuineness": 4.118232727050781, "identity": 0.17727769911289215, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/65a08c1199a2314242110e8311459eefdfb9da1f7ee0deb84d1ed84de824e689.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": "65b7538db2d820082e629cb948a1c66b9ab7fce0f276a4544aa3e35c29581182", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4cd0c682d49154c1fb1d8986b05fa70dd20050efb64cb04995e8e1013a33153a", "generation_seconds_batch": 14.991815250949003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.717686891555786, "target_z": 4.781250052914437, "ce": 6.086154937744141, "genuineness": 3.7291181087493896, "identity": 0.4428993761539459, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten!", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/65b7538db2d820082e629cb948a1c66b9ab7fce0f276a4544aa3e35c29581182.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "66e4184519c7a029e2954df583f6e4edb1ad5c432c0c24c1b8eaba19a4acc4c6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "37bf80f8340313a25a0406121e53644118ef28f3bdcaab14ca8aa0c52125de49", "generation_seconds_batch": 21.622271816944703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33439522981643677, "target_z": 0.2675781477091125, "ce": 6.23706579208374, "genuineness": 4.268857479095459, "identity": 0.39504462480545044, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/66e4184519c7a029e2954df583f6e4edb1ad5c432c0c24c1b8eaba19a4acc4c6.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": "66f92c2f8b3ade44e139f415c09f213304f2d2d5beb6fb92720e418ad6e28bca", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "948dd4a327a009b948d42e4fd86818b5644c15bdae9079fa22f56d7b37aed3d2", "generation_seconds_batch": 19.334014646010473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37358391284942627, "target_z": 0.3417968681652186, "ce": 6.173524379730225, "genuineness": 3.923675537109375, "identity": 0.550232470035553, "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_Triumph/66f92c2f8b3ade44e139f415c09f213304f2d2d5beb6fb92720e418ad6e28bca.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "6732eb6acb53b1427f4ba527a10f3acb73df2553fefbc0a8640208a92a8bd7dc", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "40de00f60db521608bc3c20a06a271d96d28bc4e1344b613ceb2ce8f656b9fdd", "generation_seconds_batch": 15.49826963210944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21592675149440765, "target_z": 0.04321289236125496, "ce": 6.292664527893066, "genuineness": 4.532451152801514, "identity": 0.5006061792373657, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6732eb6acb53b1427f4ba527a10f3acb73df2553fefbc0a8640208a92a8bd7dc.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": "673ae0f45ec48441abcd398482976d6e3e848e1899babc116a45f1b2ea8935ce", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa97b5cc19992e3baad8acf533433955e4b83cb503870c5a080b97ce638ce890", "generation_seconds_batch": 20.485435885027982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22043859958648682, "target_z": 0.05175779783829145, "ce": 6.316492557525635, "genuineness": 4.3504462242126465, "identity": 0.6970170736312866, "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_Triumph/673ae0f45ec48441abcd398482976d6e3e848e1899babc116a45f1b2ea8935ce.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "6744a8fd66fc0ff835358e7626a8d1408dda8237778a031ab2f1d9eed38901d2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8dd67bb90107a8561dae7925d5c1470d3618712540c5761e2b334c410dff6aae", "generation_seconds_batch": 21.516512061934918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7417514324188232, "target_z": 1.03906250970098, "ce": 5.927301406860352, "genuineness": 4.017816066741943, "identity": 0.6228119730949402, "hypothesis": "Ik 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_Triumph/6744a8fd66fc0ff835358e7626a8d1408dda8237778a031ab2f1d9eed38901d2.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "674cc9469051a625aee16b7f6a6698e621dd8817f9306021b58236499ba8dcff", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "20bcef3ad91b75deac580919db6c30efe4eadf6903cc8da371513bcbc1ea6371", "generation_seconds_batch": 19.2749380110763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1131853237748146, "target_z": -0.15136719334263574, "ce": 5.911416053771973, "genuineness": 4.494794845581055, "identity": 0.7914071083068848, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/674cc9469051a625aee16b7f6a6698e621dd8817f9306021b58236499ba8dcff.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "6800c3da38dceca2be3b1f1c80c0a94255ad87908e2f52677f868cb480763cf9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bc8de89a20d70ca4146e51df7bfc460cbf65d2af93592f12d31fa13262dbf9b5", "generation_seconds_batch": 16.030531330034137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3711764812469482, "target_z": 4.125000409204978, "ce": 5.839932441711426, "genuineness": 4.049196243286133, "identity": 0.4738975465297699, "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_Triumph/6800c3da38dceca2be3b1f1c80c0a94255ad87908e2f52677f868cb480763cf9.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "6827560dde780aac8ac0d9532e1675846b2d929f446dfbb1e72c20fc7268ce81", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "21b52ff89c540a9293806da5b72a1abed7be54e158900ef6b326d10d57bcc921", "generation_seconds_batch": 15.613323271973059, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6351845264434814, "target_z": 4.625000352762912, "ce": 6.340320587158203, "genuineness": 3.873466968536377, "identity": 0.32238638401031494, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6827560dde780aac8ac0d9532e1675846b2d929f446dfbb1e72c20fc7268ce81.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "686b28d9c34b12a250d6d9fe87a25f98ac682b48feb25ff130f19e95ef0bcf41", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ac0ec3a9341d00f4ba9ec5727db1f217f867f6092034758badac17ddab9da3df", "generation_seconds_batch": 20.042222104035318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6633740067481995, "target_z": 0.890624955904636, "ce": 6.078212261199951, "genuineness": 4.394378662109375, "identity": 0.6075767278671265, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/686b28d9c34b12a250d6d9fe87a25f98ac682b48feb25ff130f19e95ef0bcf41.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "68e37ed052e2b4563f88b47e198ebf6d6862bc90da414842f3613bd7a7496dd5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7b0675229b313637b04822d00935b1a4ca2b16fa9da986d0eefaacc0d314721d", "generation_seconds_batch": 22.082810263964348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37152135372161865, "target_z": 0.33789062566143047, "ce": 6.340320587158203, "genuineness": 4.469690799713135, "identity": 0.4085651636123657, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/68e37ed052e2b4563f88b47e198ebf6d6862bc90da414842f3613bd7a7496dd5.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "6924d9157a560f3fb71b61e2ddd16a5da7169945aed75aca9f166f9f37497579", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9e943e6b532ca6e0015026d5a2291da3f6e535854116401efb9d07a47189ec8b", "generation_seconds_batch": 22.324592764955014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.213993102312088, "target_z": 0.039550790013953604, "ce": 5.808161735534668, "genuineness": 3.9550557136535645, "identity": 0.3762388229370117, "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_Triumph/6924d9157a560f3fb71b61e2ddd16a5da7169945aed75aca9f166f9f37497579.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "69401b4e53db912920750b2925eecbbe8f67567e574f16f10377230eaa749e03", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "de43813fff9a18080cf2b312b91a9f5050548a1a061bc429c27e9a4bc267d796", "generation_seconds_batch": 19.733593913028017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.603559672832489, "target_z": 0.7773436975265168, "ce": 6.149696350097656, "genuineness": 4.086852550506592, "identity": 0.4707750678062439, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/69401b4e53db912920750b2925eecbbe8f67567e574f16f10377230eaa749e03.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "694d164ea1d92950e231e0da0c1fdb462951d33da0eb6a7954fbfcb69e1b78f0", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "efd34fedfea0d24aaf9a22ba6160ba0dbd10502441749d87ef1d6dd87680162d", "generation_seconds_batch": 19.996083856909536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5231197476387024, "target_z": 0.6250000141105165, "ce": 5.855817794799805, "genuineness": 4.15588903427124, "identity": 0.6980737447738647, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/694d164ea1d92950e231e0da0c1fdb462951d33da0eb6a7954fbfcb69e1b78f0.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "695c1282fc9b11adcace7f6db3e43def5711469ece0ecd5b5fba303dff2f5c22", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "17a2758c81b4eddad6cfec27240c492dbab67949bbcc8eabeb66dc29da4dcbd3", "generation_seconds_batch": 21.653649643994868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.767188549041748, "target_z": 4.87500032454188, "ce": 5.720792293548584, "genuineness": 4.080576419830322, "identity": 0.2678779065608978, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/695c1282fc9b11adcace7f6db3e43def5711469ece0ecd5b5fba303dff2f5c22.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "69fd7694bbb5e1c8f7f94bcfcffea21a9a413c3c3603b1ad8e5be4a2322231ee", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e47962174bdf889b9e22001dd58a5dec3613e5efed41e41ff8b5fbfa7865515f", "generation_seconds_batch": 19.548025041935034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2326414585113525, "target_z": 1.9687500317486621, "ce": 6.070269584655762, "genuineness": 3.886019229888916, "identity": 0.6729600429534912, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/69fd7694bbb5e1c8f7f94bcfcffea21a9a413c3c3603b1ad8e5be4a2322231ee.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "6a290c05fb0dff6cf1a5e59c181e918fccbd127daffa40113d419b9e3816ca6c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "58808398a83022733691126d67ca7fa7c4c7641dd07fc5ef71eee579894de8ce", "generation_seconds_batch": 14.329725404968485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47774332761764526, "target_z": 0.5390624532589141, "ce": 5.927301406860352, "genuineness": 3.9173994064331055, "identity": 0.4637453556060791, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6a290c05fb0dff6cf1a5e59c181e918fccbd127daffa40113d419b9e3816ca6c.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "6a2e99c6625050861faf4bb11388431cdd105c7150f7c4e760d1ce24bfcf622e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "25cff61a19a8c81a47bbf8641623108ecc9caaf69a3f9b521b5bf5f57cbb533a", "generation_seconds_batch": 20.151852617040277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8242539167404175, "target_z": 1.1953124356207685, "ce": 6.221180438995361, "genuineness": 4.143336772918701, "identity": 0.7294559478759766, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6a2e99c6625050861faf4bb11388431cdd105c7150f7c4e760d1ce24bfcf622e.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "5dd3be86eec010c88d88c1f6ef2eb77d56b32a8540753ef2e7816b96169e30f1", "generation_seconds_batch": 16.242263237014413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7252508997917175, "target_z": 1.0078124567865432, "ce": 6.467403411865234, "genuineness": 3.9676074981689453, "identity": 0.20801326632499695, "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_Triumph/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.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": "6ab2950e5865f9d0ec2efc49c433149c7966d1aa92d0211ced104a5b8892427b", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "68a0b1689b34bc9a4e89b6e723645fbcfb9683966714b2249880a1570176da21", "generation_seconds_batch": 15.582951671909541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8943811058998108, "target_z": 1.3281250194019603, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.6097316741943359, "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_Triumph/6ab2950e5865f9d0ec2efc49c433149c7966d1aa92d0211ced104a5b8892427b.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": "6b1ad989eea9b066a61c4c59f81eaa333a9f0ceec65740f5b9de257d434778ee", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3019db88131cf58b3c0b6d0e7cf7bdb1f4f90b9c50287d3428ffe677150b9b70", "generation_seconds_batch": 17.435959176975302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2061712741851807, "target_z": 3.8125001058288737, "ce": 6.403861999511719, "genuineness": 4.218649387359619, "identity": 0.3999781906604767, "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_Triumph/6b1ad989eea9b066a61c4c59f81eaa333a9f0ceec65740f5b9de257d434778ee.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "6b1d8f9d19a83f0392b8580e312c121873e279f81f07dbd46871d583a8cd0b37", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fad8ce34b17e5ed33e7ae22915318e4831b89eae4775a63b65b48d6d342211a2", "generation_seconds_batch": 15.18445967102889, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6846859455108643, "target_z": 4.718750172853827, "ce": 6.292664527893066, "genuineness": 3.9173994064331055, "identity": 0.533532977104187, "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_Triumph/6b1d8f9d19a83f0392b8580e312c121873e279f81f07dbd46871d583a8cd0b37.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": "6b3f01f030b57e30d01c2e37414f913441f2150d3427f72e0f4c209134550cea", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The road turns left behind the bridge.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89580976bfb67e90947765c0b40a8cfd4160f0b075c5b7918b97648003e50143", "generation_seconds_batch": 15.583390384097584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7417514324188232, "target_z": 1.03906250970098, "ce": 6.268836498260498, "genuineness": 3.71028995513916, "identity": 0.5300369262695312, "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_Triumph/6b3f01f030b57e30d01c2e37414f913441f2150d3427f72e0f4c209134550cea.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "6b85d39a2441c8fa2fabc18b2e5fe7cd6fc5fd920cd4ef47bc3e2779b79e3435", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2c1b1201fb0d762bf78e8a6b363e43a92b7dbd4c1ff09d5f13fa0975fd12711c", "generation_seconds_batch": 19.564025789964944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1047625541687012, "target_z": 1.7265625449772712, "ce": 6.157639026641846, "genuineness": 4.2249250411987305, "identity": 0.4141339063644409, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6b85d39a2441c8fa2fabc18b2e5fe7cd6fc5fd920cd4ef47bc3e2779b79e3435.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "f4fe5673bc99caa6e60c3f24853be9c9d006bf45be78a6d63471def801f7a513", "generation_seconds_batch": 16.01942240295466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06729330122470856, "target_z": -0.23828124426760267, "ce": 6.292664527893066, "genuineness": 4.68307638168335, "identity": 0.6975975036621094, "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_Triumph/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "6bca8949c0245c1133957bc58801c16abdb84ed54cd0b8b971c9a8de165c9482", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a9ad264a01baaac28c5c0318814c26fb3aefc4d485714006b284510c16872d32", "generation_seconds_batch": 20.231967589003034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15959300100803375, "target_z": -0.06347655357068878, "ce": 6.23706579208374, "genuineness": 3.7542223930358887, "identity": 0.24337896704673767, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6bca8949c0245c1133957bc58801c16abdb84ed54cd0b8b971c9a8de165c9482.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "6c5ab90b7aec8a497b8ae309b2638b0861174e8e94129180d6c51e288dc79e1b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ac76e36e87c9294cca0ab8a4ad69ae012c910fe839f6b5f0922c9c99a3084169", "generation_seconds_batch": 21.607772447983734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.280423641204834, "target_z": 3.9531252875017735, "ce": 6.38797664642334, "genuineness": 4.268857479095459, "identity": 0.4293016195297241, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6c5ab90b7aec8a497b8ae309b2638b0861174e8e94129180d6c51e288dc79e1b.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "6c837eba6d9c1783d28570b38c1cd77ab0f18361692019ecf13c05e8e133fe5f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7e80e24adce4407f7df1890af12edb0aab6e02cb3b778c18c76e26012da38e22", "generation_seconds_batch": 15.0303534490522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5956525802612305, "target_z": 2.6562500670249536, "ce": 5.927301406860352, "genuineness": 4.218649387359619, "identity": 0.25141602754592896, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6c837eba6d9c1783d28570b38c1cd77ab0f18361692019ecf13c05e8e133fe5f.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "6c981a8e78c47e8e5bd7b093ee0beee06de7db9387dc78a4bc24f7c19d6ee606", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6bd7dd8d0a2da0aa6c467828b7141ac224074ceda2cb7f97ae2eb35da557db37", "generation_seconds_batch": 15.298808315885253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11163840442895889, "target_z": -0.15429687522047683, "ce": 6.284721851348877, "genuineness": 4.482243061065674, "identity": 0.5591716766357422, "hypothesis": "Ik heb het iets tot een testing. Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken? Ja.", "wer": 0.4444444444444444, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6c981a8e78c47e8e5bd7b093ee0beee06de7db9387dc78a4bc24f7c19d6ee606.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "6ca706925c0702a854aa6f456b649fc07599b8f812b37b08ce3825fba2547c89", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "049999c756c3d4947adf7b382385adcb2b3094ab6ca5605e20df31d774aaadeb", "generation_seconds_batch": 14.210392058012076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3216748237609863, "target_z": 4.031250137577536, "ce": 6.475345611572266, "genuineness": 4.337893962860107, "identity": 0.5078699588775635, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6ca706925c0702a854aa6f456b649fc07599b8f812b37b08ce3825fba2547c89.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "6cf4a20714503d983dac7d28c4fdb239a70426cb8428971f6fff4c14cc132bb9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "afe04bce2e367c25ba10e489f19758b9ec0199fa1052c1be0bc0dbc129142549", "generation_seconds_batch": 19.492070795968175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2526661455631256, "target_z": 0.11279294984411266, "ce": 6.23706579208374, "genuineness": 4.3127899169921875, "identity": 0.4820622205734253, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6cf4a20714503d983dac7d28c4fdb239a70426cb8428971f6fff4c14cc132bb9.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "6d02f6bb3129017b6a865b0dc18f416450335629a7ca4d1af04948a74381a54a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b86f32c5ef121a9c555209ac1fc5170b4ae4f1e2f59db383a1632ffd4e448857", "generation_seconds_batch": 19.276610958972014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.059386134147644, "target_z": 1.640624984125669, "ce": 5.498397350311279, "genuineness": 3.747946262359619, "identity": 0.45785650610923767, "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_Triumph/6d02f6bb3129017b6a865b0dc18f416450335629a7ca4d1af04948a74381a54a.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "6e2622a38205c6e1d454f4c32f65b986b39733552f9ad00def9227a63a8cf17e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "363210faec1eca58edc0c15ff1191f4b6f4373dc26cca4e202ca2841f61f8d0f", "generation_seconds_batch": 19.29187605297193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09410661458969116, "target_z": -0.18750000705525824, "ce": 6.221180438995361, "genuineness": 3.986435890197754, "identity": 0.35760432481765747, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6e2622a38205c6e1d454f4c32f65b986b39733552f9ad00def9227a63a8cf17e.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "6e545a2c6e24d5427fdca2d6df41760e32a83b252d00340f5e5cb87ec969491c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7a23064491d2256c91288e1d2e524ec41621cc8bd26aa3b280ed558b7d669570", "generation_seconds_batch": 19.25428751099389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3374890685081482, "target_z": 0.27343751146479467, "ce": 6.221180438995361, "genuineness": 4.256305694580078, "identity": 0.5994967222213745, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6e545a2c6e24d5427fdca2d6df41760e32a83b252d00340f5e5cb87ec969491c.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "6ed919aff56d1046dee63bb7415a48dfec70ccd1d7a7c7756525fb0b6bf7b1f5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f641ce722d094520d6ca2e5957c4335c6a7a2c876bc9491e17b8617a0b3368a1", "generation_seconds_batch": 21.186136418022215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14128774404525757, "target_z": -0.09814454045490725, "ce": 6.348263263702393, "genuineness": 4.632867813110352, "identity": 0.6341817378997803, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6ed919aff56d1046dee63bb7415a48dfec70ccd1d7a7c7756525fb0b6bf7b1f5.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "6ee42eabbb070974b080c255d25451cc0bc8f2fab7cc0d0a912460c3c6325460", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c092446245341573d06d567ce2814620fa229b7cf767bd23153f91d7b8d3ad5", "generation_seconds_batch": 21.951821477035992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4718987941741943, "target_z": 2.4218750652611387, "ce": 6.221180438995361, "genuineness": 4.262581825256348, "identity": 0.6165868639945984, "hypothesis": "¡He encontrado la cajita! Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6ee42eabbb070974b080c255d25451cc0bc8f2fab7cc0d0a912460c3c6325460.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": "6f04c26f57c94413dd01edfd0861dddcab4368ef6aaf307c6ae17cf64695650b", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25611fe372d92c3daa32721c6419f21d9035e21759d7d8e36a56d6bd6a49dc9a", "generation_seconds_batch": 15.49750205304008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9645082354545593, "target_z": 1.46093749029902, "ce": 6.070269584655762, "genuineness": 4.168440818786621, "identity": 0.5526779890060425, "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_Triumph/6f04c26f57c94413dd01edfd0861dddcab4368ef6aaf307c6ae17cf64695650b.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "6f568890f4de6306574a39fe4491f96cecf46fdbe52f9dabcbf190f7eef7ad5f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9b9cd902a64b88c7ce9da7762b35123074b2bfdc3a575c1c04bc12bad81c0afa", "generation_seconds_batch": 21.7691732380772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.087228775024414, "target_z": 7.37500004233155, "ce": 5.6334228515625, "genuineness": 3.8169827461242676, "identity": 0.3981319069862366, "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_Triumph/6f568890f4de6306574a39fe4491f96cecf46fdbe52f9dabcbf190f7eef7ad5f.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": "6f914b81292df37c8e7742dc16652c102dfefac9edca2ce2721ffa648e1433ab", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8cf32efa63904457b29f826914cbbe4017cfadb3b1c4f0b28890d5ce1145f4e1", "generation_seconds_batch": 19.667238306021318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04976151883602142, "target_z": -0.2714843619918676, "ce": 6.205295085906982, "genuineness": 4.394378662109375, "identity": 0.43464094400405884, "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_Triumph/6f914b81292df37c8e7742dc16652c102dfefac9edca2ce2721ffa648e1433ab.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "6fcd4b3c73af35560de1867c1a72cc963ebc0122160f9800f02fda5dc4ffcca6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7eda32947fef097524595bb23f25b6e11f04ec66038d5a7877bd0c388fa7d1d0", "generation_seconds_batch": 17.91572921804618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34470802545547485, "target_z": 0.28710936022805306, "ce": 5.998785495758057, "genuineness": 4.18099308013916, "identity": 0.4834122657775879, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/6fcd4b3c73af35560de1867c1a72cc963ebc0122160f9800f02fda5dc4ffcca6.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "700e7b494a0b30619f1dadb03b54aefa56b9e52de307431430b5f9435b5c2273", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a40dff80b24fcb62a4201f995837c93e56731c7e728fe555f06c3e04b39dad22", "generation_seconds_batch": 22.35543948900886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2886738777160645, "target_z": 3.968750257516926, "ce": 6.0305562019348145, "genuineness": 4.262581825256348, "identity": 0.7346916198730469, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/700e7b494a0b30619f1dadb03b54aefa56b9e52de307431430b5f9435b5c2273.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "702d8e2ea148f827b019b81502743582365b70697d4ab0f60c054295cc62b947", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "398a705a00b4f75b8014f5a1e6a404184c2e458838ff917bbd6546cad52a0c66", "generation_seconds_batch": 15.251963375951163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.19792103767395, "target_z": 3.796875135813721, "ce": 5.903473377227783, "genuineness": 4.18099308013916, "identity": 0.5145930051803589, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/702d8e2ea148f827b019b81502743582365b70697d4ab0f60c054295cc62b947.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "71012f550e6c8d4c679dc453d0f1693e3264edc75782f3c611003a7d6fc4a611", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4c36a54c7efb228776660a7a5da8e84b5e19c567bac65fc8c7a6799f625c7703", "generation_seconds_batch": 17.501206881017424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0882620811462402, "target_z": 1.6953126049469665, "ce": 6.125868320465088, "genuineness": 4.017816066741943, "identity": 0.6910498738288879, "hypothesis": "Je trouvai la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/71012f550e6c8d4c679dc453d0f1693e3264edc75782f3c611003a7d6fc4a611.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "715e04fdc7dd7ec0111e935d1bf91b53081c666ada1eeef3d70605c8c63f21de", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "805da09409051f8e3ef0dd04e6ea7c16fe716d41cbaf9250c7abd330c6217605", "generation_seconds_batch": 21.007641253992915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7046252489089966, "target_z": 0.9687499188645301, "ce": 6.1894097328186035, "genuineness": 4.507347106933594, "identity": 0.3871755301952362, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/715e04fdc7dd7ec0111e935d1bf91b53081c666ada1eeef3d70605c8c63f21de.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "7160b38d88935bb76176d11bc26dd793ff896da1bef82afbb9c3f25b2ecad4b6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "23f19d6fe0b7dcffe720161b9eec270d6cbca421f814e628f0af262b865d9fd1", "generation_seconds_batch": 19.310675690998323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14515505731105804, "target_z": -0.09082030753927155, "ce": 6.372091293334961, "genuineness": 4.168440818786621, "identity": 0.5113840103149414, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7160b38d88935bb76176d11bc26dd793ff896da1bef82afbb9c3f25b2ecad4b6.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "71effe4e5153fdf5178c3b68e1a7c30fd25bdbdb1ea594cbf4803da9d00b4455", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "17c367dfd5a3119eff72549434c69963da7ab4cd53dea9f5714ea40fb02e7b3f", "generation_seconds_batch": 20.728050720063038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14618633687496185, "target_z": -0.08886718628737748, "ce": 6.260893821716309, "genuineness": 4.293961524963379, "identity": 0.6418872475624084, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/71effe4e5153fdf5178c3b68e1a7c30fd25bdbdb1ea594cbf4803da9d00b4455.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "7201decdd05d324a64316dc7f3d72bba483f6f9f0b9b95fe0b8c9c95bb47304f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2aede6f9993b6fb725bd394ab24df9a185e32e5740bbf7ac0039ba623cae6b66", "generation_seconds_batch": 21.40187646704726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24957230687141418, "target_z": 0.1069335860884305, "ce": 5.998785495758057, "genuineness": 3.71028995513916, "identity": 0.4315873980522156, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7201decdd05d324a64316dc7f3d72bba483f6f9f0b9b95fe0b8c9c95bb47304f.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "72629d5a650e63f3e40b875d9105b8f68f4527a521ca860b39575421e45e7f12", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1bc7c8d6f832002af652ebe53619eeaf3aad8046fe707230a9220c39ada5e85e", "generation_seconds_batch": 20.724042073008604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35708341002464294, "target_z": 0.31054687169284767, "ce": 5.335572719573975, "genuineness": 3.6789097785949707, "identity": 0.06147236377000809, "hypothesis": "De deur 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_Triumph/72629d5a650e63f3e40b875d9105b8f68f4527a521ca860b39575421e45e7f12.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": "73d85bb5d5e8016b79d18d047250c2602e969763bd87facf86fc161219166add", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "113cca306995489df56dd70f4c707d9cd07eed03bc20ca72f006cca5f421f333", "generation_seconds_batch": 16.239154539071023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5354951024055481, "target_z": 0.6484374691332452, "ce": 6.157639026641846, "genuineness": 4.243753433227539, "identity": 0.5366427898406982, "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_Triumph/73d85bb5d5e8016b79d18d047250c2602e969763bd87facf86fc161219166add.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "74d26fdbbb04dda2cd2a9ede79665f4f11ae670e97b874789aabaf0735620252", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e65edfd354e8e289521d7fd33939248f29621ac1634ab23be8e87316e23f2745", "generation_seconds_batch": 22.19570771092549, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4344295263290405, "target_z": 0.4570312477952318, "ce": 5.982900142669678, "genuineness": 4.243753433227539, "identity": 0.4528904855251312, "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_Triumph/74d26fdbbb04dda2cd2a9ede79665f4f11ae670e97b874789aabaf0735620252.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "751dd771ca96aaf453a43a92e63df3d13c1435adc296ee91e9b1d40cce65c5b1", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "484b9a4a587ef4882be70681e974b85931f4e49e4b22f144a9b61d510ee9fc3e", "generation_seconds_batch": 19.387413332005963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6138725280761719, "target_z": 0.7968750229295893, "ce": 6.157639026641846, "genuineness": 4.645420074462891, "identity": 0.5584201812744141, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/751dd771ca96aaf453a43a92e63df3d13c1435adc296ee91e9b1d40cce65c5b1.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": "7573253ed1d283d754e30f78231f37d8f1b4e9e62befe5bd84afb3aa23657817", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I wrote the number on the envelope.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68104fcc665a7b8815b043dbc76dd3d665bd0adfe5fc6739920991a2d9c3e0e2", "generation_seconds_batch": 16.078394017997198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9108815789222717, "target_z": 1.359374959432265, "ce": 6.157639026641846, "genuineness": 3.6663577556610107, "identity": 0.3556302785873413, "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_Triumph/7573253ed1d283d754e30f78231f37d8f1b4e9e62befe5bd84afb3aa23657817.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "759ea79629c2a80ba246184114c525baec0709d1e2164b81870007031b0d22bb", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "533007d82fe7da12f1b853fb012a28f0ee8ba845ec63ad022e185c2ba8396621", "generation_seconds_batch": 20.892394803930074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2683931887149811, "target_z": 0.142578105377563, "ce": 6.229123115539551, "genuineness": 4.720732688903809, "identity": 0.500118613243103, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/759ea79629c2a80ba246184114c525baec0709d1e2164b81870007031b0d22bb.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "75a77c21788e02eedac6f2d4f6b1e91ed463a8f0e80da35aeaf7757087d20de6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "37fc50c864fa0e8bac204e1cde046a376feeb8a1ece8a86a2fe37cf3b9e2ae68", "generation_seconds_batch": 15.763659035903402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10751327872276306, "target_z": -0.16210937433856953, "ce": 5.919358730316162, "genuineness": 4.3881025314331055, "identity": 0.6522120833396912, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/75a77c21788e02eedac6f2d4f6b1e91ed463a8f0e80da35aeaf7757087d20de6.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": "7638e8e3a7b25c59a064ebaa18a4e431fee64e393c161ce364396af403d11c62", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af4c5756f2315a0c019cc8cc9ed804245b17dcdc21aa6a4d3f187a72275e7665", "generation_seconds_batch": 17.248792842030525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055949196219444275, "target_z": -0.25976563448050327, "ce": 6.205295085906982, "genuineness": 4.3881025314331055, "identity": 0.5525420308113098, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zum kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7638e8e3a7b25c59a064ebaa18a4e431fee64e393c161ce364396af403d11c62.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "76aead4dfe7934da25f394359a30e59b3cdf63c535441cd1dcdc8070c28d44cc", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed2bc5990512a13a4eb78049933b8862254d70ea2cc8d037b4cb5968447ec6a5", "generation_seconds_batch": 22.251561678946018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.833190441131592, "target_z": 5.000000084663099, "ce": 5.689021587371826, "genuineness": 4.005263805389404, "identity": 0.34296926856040955, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/76aead4dfe7934da25f394359a30e59b3cdf63c535441cd1dcdc8070c28d44cc.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "7707d9867b21a97d8c922441c22d9b49c928a62e36a66f1d1761c62cb3c38f59", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d980d16e58c49c769af72b6c3003c8b5d43517aa42e2dfbb5309928adb225520", "generation_seconds_batch": 22.553385852021165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10132558643817902, "target_z": -0.17382813007096687, "ce": 6.205295085906982, "genuineness": 4.268857479095459, "identity": 0.5805943012237549, "hypothesis": "Niek, ik heb het 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_Triumph/7707d9867b21a97d8c922441c22d9b49c928a62e36a66f1d1761c62cb3c38f59.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "774da4386c9ae2f319127bad6b7c517c295e0ed9140c8d6a422c7efb245f5655", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65853d794e5edb2e55dd6049654c0942a27ebc31c57d51e5ef82a29b19274e1d", "generation_seconds_batch": 23.035680811968632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3711764812469482, "target_z": 4.125000409204978, "ce": 5.355429172515869, "genuineness": 3.9801597595214844, "identity": 0.5659747123718262, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/774da4386c9ae2f319127bad6b7c517c295e0ed9140c8d6a422c7efb245f5655.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "2194695462e5d62f3bf88b0b186f15b04bdf81a2e3f86b6c05201628ab4bcc6c", "generation_seconds_batch": 14.852656758041121, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03429229557514191, "target_z": -0.3007812372123444, "ce": 6.213237762451172, "genuineness": 4.582659721374512, "identity": 0.730803370475769, "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_Triumph/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "78739aea0ea1874e096295349b56e8bd64ef0011be48301f2cf1ebaaed4f85d8", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6f90088c663e19183ba948e89725a1543914acd7bdefc0a07a74a3c2a2b07723", "generation_seconds_batch": 16.240595448063686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16010864078998566, "target_z": -0.06249999294474175, "ce": 5.780362129211426, "genuineness": 3.71028995513916, "identity": 0.14168712496757507, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/78739aea0ea1874e096295349b56e8bd64ef0011be48301f2cf1ebaaed4f85d8.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "78c0049f2d9f4e2dd8ea89ebc35809070775c450dc67397fe3231494b8c60d48", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b37bcb3edda0fcd771f8aa39bd2669f4a3ad1d47afb860119527d599ba5a99b9", "generation_seconds_batch": 14.489745410042815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14567069709300995, "target_z": -0.08984374691332452, "ce": 5.752562999725342, "genuineness": 3.8922953605651855, "identity": 0.5763869285583496, "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_Triumph/78c0049f2d9f4e2dd8ea89ebc35809070775c450dc67397fe3231494b8c60d48.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "78d40b137a969aa74e66eb42bb38d3756b5ef26500c71ecb4e452f692fa4fbbb", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "905cebf13415163bf36d016f8212f0ef555143fa965561fa172527947c6a924a", "generation_seconds_batch": 22.45248657197226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0470107793807983, "target_z": 1.6171875291029403, "ce": 6.173524379730225, "genuineness": 4.381826400756836, "identity": 0.6555396318435669, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/78d40b137a969aa74e66eb42bb38d3756b5ef26500c71ecb4e452f692fa4fbbb.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "792ba4996ae55ee8ec011c0cdec3c333462a156eeaf6ec80a190cbf280872087", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d4447e8eeccd58e6fed7afed778de3823602ece57c61f03837d2571b3cdf23b5", "generation_seconds_batch": 15.953835360938683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24879884719848633, "target_z": 0.10546874514950995, "ce": 6.205295085906982, "genuineness": 4.362998008728027, "identity": 0.5254078507423401, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/792ba4996ae55ee8ec011c0cdec3c333462a156eeaf6ec80a190cbf280872087.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "7949c36bebf8c4bf22462e5dbf17b7faab163e165bc13b0ec293b19952816dc5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "12ec60e6fd7369301a39ab0b87fe5df6351c9ea6c981b54d8ad6dc84984bbb97", "generation_seconds_batch": 19.276610958972014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24544718861579895, "target_z": 0.09912110108085427, "ce": 5.637393951416016, "genuineness": 3.8546390533447266, "identity": 0.376584529876709, "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_Triumph/7949c36bebf8c4bf22462e5dbf17b7faab163e165bc13b0ec293b19952816dc5.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "a5f5301eabfd960d95b0bffe10e1ab2b6fd5ad697f2b47bbccb3122238d2c032", "generation_seconds_batch": 15.16460825491231, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07451226562261581, "target_z": -0.2246093813938278, "ce": 6.213237762451172, "genuineness": 4.419482707977295, "identity": 0.4346689283847809, "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_Triumph/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "79a2031d9f1356a5f702b7a06ac5bf21b7118b79b2099c7bfced68a7d8ef9e50", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2764bed50ccb1118cd138eadcfed3c5b616f6e1b1cd7ca08cc277f8d6cbe243e", "generation_seconds_batch": 16.71561454399489, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.509711265563965, "target_z": 6.281250335124767, "ce": 5.911416053771973, "genuineness": 3.998987913131714, "identity": 0.2744409441947937, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/79a2031d9f1356a5f702b7a06ac5bf21b7118b79b2099c7bfced68a7d8ef9e50.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "7ad6715580bda96b548d6ed2c972eea0adfa5e03f75de834b15721c4e89387f4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99930f9104cb9a72438f40da011d5d93723ddc27114813548bb07cf5303285ca", "generation_seconds_batch": 21.43845537607558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2952046394348145, "target_z": 5.875000211657747, "ce": 6.181467056274414, "genuineness": 3.9425034523010254, "identity": 0.09737828373908997, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7ad6715580bda96b548d6ed2c972eea0adfa5e03f75de834b15721c4e89387f4.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "7aebe73d155ad0f8dedddd112ec0219394be46baa3109b9d1cfee192680840c4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fd70c91b1cd28afc9140bfd3ae5810bb7a4009444fcab12a0ce7172c39584780", "generation_seconds_batch": 21.25957598804962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5379008054733276, "target_z": 2.5468750511506224, "ce": 6.173524379730225, "genuineness": 3.9801597595214844, "identity": 0.6724803447723389, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7aebe73d155ad0f8dedddd112ec0219394be46baa3109b9d1cfee192680840c4.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "7b3d1d38846cbcb9803b34ce44451c077218fa35e4adfe17fd0557f04c60922b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "30bc6619f6c460e3f8b29d82142e990b684ed93878389d5685ee1b6e6cf5a764", "generation_seconds_batch": 14.841955462936312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5334325432777405, "target_z": 0.644531226629457, "ce": 6.332377910614014, "genuineness": 4.425758361816406, "identity": 0.5896810293197632, "hypothesis": "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_Triumph/7b3d1d38846cbcb9803b34ce44451c077218fa35e4adfe17fd0557f04c60922b.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "7bb4cae62b2bddb2a50ae7ab17457a5cbf48aac94570c94348613647701000a5", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dc549be8479def58afe8afe2479af06ef59f0602d60f2b3b022c5000b3dbfd8b", "generation_seconds_batch": 14.853941571083851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20000633597373962, "target_z": 0.013061512482557991, "ce": 6.141753673553467, "genuineness": 4.645420074462891, "identity": 0.6230851411819458, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7bb4cae62b2bddb2a50ae7ab17457a5cbf48aac94570c94348613647701000a5.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "7bc565d573cab589d54356c8edf188833dab7c79439cbe39ab93d9f368e63955", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e175a13e64a9e1cd546f3b61f8fdf2330cb88b542b362124707265f2a8efa500", "generation_seconds_batch": 15.109354506013915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16436266899108887, "target_z": -0.05444336778067877, "ce": 5.6532793045043945, "genuineness": 3.8671910762786865, "identity": 0.5430863499641418, "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_Triumph/7bc565d573cab589d54356c8edf188833dab7c79439cbe39ab93d9f368e63955.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "7c00d39c965dc02165a5d757bef3c2f658d0fb6c9661dfa634d93923de097c51", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b8e4d5bb6b0d4b073c8345a3d5c6403e549cbab1855b30c69d4686afb15c62c4", "generation_seconds_batch": 15.02564369305037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.420677900314331, "target_z": 4.218750229295893, "ce": 6.435632705688477, "genuineness": 4.281409740447998, "identity": 0.4779973328113556, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7c00d39c965dc02165a5d757bef3c2f658d0fb6c9661dfa634d93923de097c51.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "7c043ab111bb9cb824e1d8b9aa9820050f517394afca88780ef0d734aeeab6c5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1fd7cfc7a2ed346d0e187a5ba89e24e0b480810b2e444e8888ca49b163a5e520", "generation_seconds_batch": 19.967199723003432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2226300835609436, "target_z": 0.05590820871959932, "ce": 6.157639026641846, "genuineness": 4.293961524963379, "identity": 0.6834365129470825, "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_Triumph/7c043ab111bb9cb824e1d8b9aa9820050f517394afca88780ef0d734aeeab6c5.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "7c5b1c42c8d5fc430ffa714fd100ebc19d285e15398fcad4dba4768fd8c006f1", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "20f9cceebd57ad8fc6fb1076cc466b29f04da9a3dd8b705e04a2aeac11f1777d", "generation_seconds_batch": 19.55016930110287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5856828689575195, "target_z": 4.53125008113547, "ce": 6.316492557525635, "genuineness": 3.9048471450805664, "identity": 0.42166662216186523, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7c5b1c42c8d5fc430ffa714fd100ebc19d285e15398fcad4dba4768fd8c006f1.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": "7c5ba825f534e6d894b1e80293f3b893ac87ee0a49288ad8131c6efdff630670", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fabdfb04a5a5df9f20d491bda955f178eb3705a58bafbaaf0c66ec6727ca5af8", "generation_seconds_batch": 19.710713403997943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10132558643817902, "target_z": -0.17382813007096687, "ce": 6.149696350097656, "genuineness": 4.2249250411987305, "identity": 0.6061344146728516, "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_Triumph/7c5ba825f534e6d894b1e80293f3b893ac87ee0a49288ad8131c6efdff630670.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "7cfdc40e8f4669eb61f57a24257f8c5ca52b7782da69b4c269bd2bcabf9e1e45", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7e18fbbca4f20297d91bb19c1442e0efd7a9453a05efec19629991714a9a8a3f", "generation_seconds_batch": 19.372387353912927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4306474924087524, "target_z": 2.3437499894171125, "ce": 5.692992687225342, "genuineness": 4.111956596374512, "identity": 0.5175503492355347, "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_Triumph/7cfdc40e8f4669eb61f57a24257f8c5ca52b7782da69b4c269bd2bcabf9e1e45.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "7d609719370b02a758be69cbcd869739d0dd488c5f9f7ed965a4e76dd1305329", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cfc5aa6a5262dc06a28dc24069de3d4064603539988551440755b0efc13c0d78", "generation_seconds_batch": 15.079659659066238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11163840442895889, "target_z": -0.15429687522047683, "ce": 6.324435234069824, "genuineness": 3.961331605911255, "identity": 0.18629978597164154, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7d609719370b02a758be69cbcd869739d0dd488c5f9f7ed965a4e76dd1305329.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "7d7cf717db63acb1b4bb1757b888147845292b5dcf6dac424618710373e38d5a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b87b91b0ba114cbc5f5f6a5c1c4647ea644df558628c323ec9474489a3cc3042", "generation_seconds_batch": 20.83719370700419, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.740718364715576, "target_z": 6.718750398622091, "ce": 5.863759994506836, "genuineness": 3.961331605911255, "identity": 0.28364911675453186, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7d7cf717db63acb1b4bb1757b888147845292b5dcf6dac424618710373e38d5a.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "7e33a4c6f580ad871512ed44bfaa85d7a1bc6800631fa44be4051201e06562ee", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ffb4a39bfcbd915cafa6882ca881f06d2520c439d8f0148413ce2a175cb73d8a", "generation_seconds_batch": 16.375231671030633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07760611176490784, "target_z": -0.21875000352762913, "ce": 6.3641486167907715, "genuineness": 4.406930446624756, "identity": 0.5573059320449829, "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_Triumph/7e33a4c6f580ad871512ed44bfaa85d7a1bc6800631fa44be4051201e06562ee.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": "7e4f356502944a9b41d400ccd8cf0749c7d09e50463637678bfe29c621007417", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f287d83d97e25ee28e303f7e6dc77e4240824335d46bbfa7cb5c03efb3b4ae69", "generation_seconds_batch": 21.44198712706566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13071711361408234, "target_z": -0.11816406150785431, "ce": 6.1020402908325195, "genuineness": 4.595211505889893, "identity": 0.5624891519546509, "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_Triumph/7e4f356502944a9b41d400ccd8cf0749c7d09e50463637678bfe29c621007417.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "7e76d0eca3c1e1846deb6eb7ab84243a697e205f10cb7e4804bc043aa382f1af", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7dfbaadeaeb2998e966b5e0c83645f5b8fe79d22293b7f45e55d1bbcc2cf91e0", "generation_seconds_batch": 14.710360034951009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.509711265563965, "target_z": 6.281250335124767, "ce": 5.911416053771973, "genuineness": 3.9927117824554443, "identity": 0.341398686170578, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7e76d0eca3c1e1846deb6eb7ab84243a697e205f10cb7e4804bc043aa382f1af.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "7eb761da4cc122b56ed68096f1989f3f78b201321159aa15b33fc1a3f5e3165c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3871abc5f2445ba56c827c72e25d1992d3cc60f8395b8d10bc775354ad327b74", "generation_seconds_batch": 20.484057481051423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9851338863372803, "target_z": 1.500000028221033, "ce": 5.804190158843994, "genuineness": 4.319066047668457, "identity": 0.6395094394683838, "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_Triumph/7eb761da4cc122b56ed68096f1989f3f78b201321159aa15b33fc1a3f5e3165c.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "7f538ba58b162d5d2ef9db7c4365f9765d8a4555e271e2b3567116ab366f82c9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8b9c58268c210dbad8e6130be8d4f1ac4010f82a537f728504d958e84bad340a", "generation_seconds_batch": 15.269302716013044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22714194655418396, "target_z": 0.06445314241766881, "ce": 6.149696350097656, "genuineness": 3.785602569580078, "identity": 0.14199727773666382, "hypothesis": "En ja, nog nooit! Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.2222222222222222, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7f538ba58b162d5d2ef9db7c4365f9765d8a4555e271e2b3567116ab366f82c9.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "a4672b265d2aba032a8684f37ce3baeba68780ab1dd2e9d77951c66e29ddf71d", "generation_seconds_batch": 16.497422083979473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01676049828529358, "target_z": -0.33398438315764234, "ce": 6.507116317749023, "genuineness": 4.595211505889893, "identity": 0.36759236454963684, "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_Triumph/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "7f71af95ee6532f18d2a71aff10298056f003ea2fe9bc3748f8082a0317d554f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "70a5e481f810ff267d1f3fc4b0b30e9145b4de44806692e3aefc60a5e1dafdf6", "generation_seconds_batch": 22.251561678946018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.460209608078003, "target_z": 6.187500063497324, "ce": 6.006728172302246, "genuineness": 4.143336772918701, "identity": 0.3500927686691284, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7f71af95ee6532f18d2a71aff10298056f003ea2fe9bc3748f8082a0317d554f.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "7f7da9646c864e258c712f4339a1d3b033490e27403a99c47b05c8ac751d8823", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "abd5556cb10513528e189a90156d46236d266990a799487cc332332b9793519d", "generation_seconds_batch": 19.57290887203999, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8283790349960327, "target_z": 1.2031249206283448, "ce": 5.285930633544922, "genuineness": 3.911123275756836, "identity": 0.437480628490448, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7f7da9646c864e258c712f4339a1d3b033490e27403a99c47b05c8ac751d8823.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "7f8ab6c5f303c41d6d4d481b1e77538438891e06b3b38b85c7f79fed8500de5a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b33da7b6536143aa10ceb75d21af2529880aa219b1575be95ac5e5bb30fec5ea", "generation_seconds_batch": 21.209933319012634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6417152881622314, "target_z": 6.5312503069037335, "ce": 6.308549880981445, "genuineness": 4.124508857727051, "identity": 0.32524818181991577, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7f8ab6c5f303c41d6d4d481b1e77538438891e06b3b38b85c7f79fed8500de5a.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "7fb1aa15ff38e01c41ea475310e78fcaf5082c3fa742f795d77111bbc55e47a8", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "813e46d728473b6520aea0db0044781bd8814a615b16d559f6d91a7b0fb488ab", "generation_seconds_batch": 20.91279345494695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1871797740459442, "target_z": -0.011230475419423815, "ce": 6.157639026641846, "genuineness": 4.017816066741943, "identity": 0.3710000216960907, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/7fb1aa15ff38e01c41ea475310e78fcaf5082c3fa742f795d77111bbc55e47a8.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "800aa8a71402fcc9d642a01d93c80a836c855988f18cccfd22f41438301b2581", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9fc5473b717835934569b4d2ebf52bd0b9c2c2320eef8eb6d0113710f668c50d", "generation_seconds_batch": 20.898307967931032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17532004415988922, "target_z": -0.033691398037238446, "ce": 6.125868320465088, "genuineness": 4.469690799713135, "identity": 0.4461446702480316, "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_Triumph/800aa8a71402fcc9d642a01d93c80a836c855988f18cccfd22f41438301b2581.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "80812414851f88b3575d273c9949064150d371d4584512079157df5ef1b53ab5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8d7e1aadf8e168758fb6730bca4e5e463a57d5fa194a27e72baf98308249a2d6", "generation_seconds_batch": 22.553385852021165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26426807045936584, "target_z": 0.13476562036998677, "ce": 5.959072113037109, "genuineness": 4.2249250411987305, "identity": 0.49036842584609985, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/80812414851f88b3575d273c9949064150d371d4584512079157df5ef1b53ab5.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "80b025f71485e31cea1de43327f248790a3f623ea73ba76de66006de24f96232", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f0b2142f2dc21c9db149c5c2e46c64919efd87b105a17208da4623c2edb698c8", "generation_seconds_batch": 20.046443048049696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7747524380683899, "target_z": 1.1015625026457219, "ce": 6.205295085906982, "genuineness": 4.444586753845215, "identity": 0.6820734739303589, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/80b025f71485e31cea1de43327f248790a3f623ea73ba76de66006de24f96232.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "d71d350ee0f6a41ab569a53d641574d2e77f5d81832dd2f1a61b4833a998831b", "generation_seconds_batch": 14.775275727035478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055949196219444275, "target_z": -0.25976563448050327, "ce": 6.443574905395508, "genuineness": 4.281409740447998, "identity": 0.5217446088790894, "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_Triumph/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.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": "818063982d9e8f65f30fa43e515d5303a52e6a8199bbd58177f401e896721850", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The keys are on the kitchen table.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f1b1e3df4dd530837ec7f11f356d5a5c4526ad751cdd6b19961629b5377ece50", "generation_seconds_batch": 16.92890536505729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2967534363269806, "target_z": 0.1962890526887815, "ce": 6.070269584655762, "genuineness": 3.9048471450805664, "identity": 0.47518080472946167, "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_Triumph/818063982d9e8f65f30fa43e515d5303a52e6a8199bbd58177f401e896721850.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "8187f23b7bc2db626ed5ff4ca74ef57a1e3ec76c46f6b85728cc4612fa0f4ca2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "155f898a2a95d521ae5bdaad0944b8c2f48b5bce1d21c784f730194c980f881f", "generation_seconds_batch": 20.54424153699074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25240832567214966, "target_z": 0.11230466953113914, "ce": 6.213237762451172, "genuineness": 4.243753433227539, "identity": 0.6053286790847778, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8187f23b7bc2db626ed5ff4ca74ef57a1e3ec76c46f6b85728cc4612fa0f4ca2.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "8267631e35905151c60093ceebdc1060d40ace48f8829f3d3b05292d322d6a2f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c87c7f21c82f56e6e32503f7f6be32aaec3ddf3cbd800b453077e79ca4a4ff89", "generation_seconds_batch": 20.0103534309892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8737554550170898, "target_z": 1.2890624814799472, "ce": 6.117925643920898, "genuineness": 4.331617832183838, "identity": 0.5515776872634888, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8267631e35905151c60093ceebdc1060d40ace48f8829f3d3b05292d322d6a2f.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "82bb6d773bbc6a96ccc96cb676099a8e563645040f9e7f6eca911ebbe845a8f7", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3b3fb7aa573843cbab752d232e4d070460573c255bd5875119ea8f1c75e8a73e", "generation_seconds_batch": 19.238406587042846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5788089632987976, "target_z": 0.7304687874810595, "ce": 6.324435234069824, "genuineness": 4.482243061065674, "identity": 0.5387088656425476, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/82bb6d773bbc6a96ccc96cb676099a8e563645040f9e7f6eca911ebbe845a8f7.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "82db57cfe52640723d2d16dece1407687ac5e6370c1f3e162627b62e6bfd26a6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8501ec7cb64aa00d369b597a7de8c36201c00e009f7a938d590b66ab82443a81", "generation_seconds_batch": 22.257823209976777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36017727851867676, "target_z": 0.3164062918905959, "ce": 6.038498878479004, "genuineness": 4.068024158477783, "identity": 0.2615940570831299, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/82db57cfe52640723d2d16dece1407687ac5e6370c1f3e162627b62e6bfd26a6.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "82f7df895cbe5e71bdf6301db3643357db5fc293dd4b92cb0be067335f44541d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "20a82f7025a422275d69b6b478461fa75a43670d81df55a2fc486b1636dabc4c", "generation_seconds_batch": 21.8557265130803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21605566143989563, "target_z": 0.04345703251774172, "ce": 6.213237762451172, "genuineness": 4.030367851257324, "identity": 0.5476762056350708, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/82f7df895cbe5e71bdf6301db3643357db5fc293dd4b92cb0be067335f44541d.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "835749225c6c74681c0a5b4d40189acdd82f2fcc6c36ff53a7782e8de5cbfe7b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f6ee9c1e35e8be06ff1083528a40fb100bcacad7fc41b51746bc22d73b51cd9f", "generation_seconds_batch": 20.349636319093406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5684961080551147, "target_z": 0.7109374620779869, "ce": 5.689021587371826, "genuineness": 3.973883628845215, "identity": 0.5613973140716553, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prête.", "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_Triumph/835749225c6c74681c0a5b4d40189acdd82f2fcc6c36ff53a7782e8de5cbfe7b.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "846e826ea90ee09e8333e3b9ef74ade74da513c3ed96daf47f886b71b24f7763", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4b8b2cc8f8705516cce4e6c959cc5d0ac3863889226c63a1b88c22dd0a49148b", "generation_seconds_batch": 19.30284366104752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032229721546173096, "target_z": -0.30468750793716554, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.7643956542015076, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/846e826ea90ee09e8333e3b9ef74ade74da513c3ed96daf47f886b71b24f7763.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "84f802009235a4fee8e41afe6016b6d03d983363c3c19b656a52bb06aa7e90a9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f8a5d40f088b84d549bab5ac5bf494272772c1ecff5d594a95aad0b04d55a949", "generation_seconds_batch": 14.4445556740975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8242539167404175, "target_z": 1.1953124356207685, "ce": 5.9431867599487305, "genuineness": 4.582659721374512, "identity": 0.4851556420326233, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/84f802009235a4fee8e41afe6016b6d03d983363c3c19b656a52bb06aa7e90a9.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": "85369c490c26436568bad1527cdcd631c3f314156b7c0b9ff711d63a9596b1f8", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d22841ba98f889090fc608f0ac51fc36c28671ed8f96951a36f3c5ce28bfb8ea", "generation_seconds_batch": 14.63687947706785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2903932332992554, "target_z": 2.078125047622993, "ce": 6.022613525390625, "genuineness": 4.143336772918701, "identity": 0.6431254744529724, "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_Triumph/85369c490c26436568bad1527cdcd631c3f314156b7c0b9ff711d63a9596b1f8.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "86884f6e8416bf8a19d95250b8cee47e60ddf03bc88ff081260b6a0b8170f80c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ad30e9d0fcfb02ee58007c43b04e85712b2491c438803a2fb0e2c1c18a0dd3ea", "generation_seconds_batch": 23.787095746025443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3395516276359558, "target_z": 0.27734375396858274, "ce": 5.824047088623047, "genuineness": 4.168440818786621, "identity": 0.6209566593170166, "hypothesis": "La porte est encore ouverte ! J'ai posé ton manteau sur la chaise ! Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/86884f6e8416bf8a19d95250b8cee47e60ddf03bc88ff081260b6a0b8170f80c.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "872b59ba244388bd7306be7670e8fdcb4b990ff853fd434e9045572b18b9d457", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8b8acbbcfa474cbfab9ab4da4332ce111f740ebd15249eb9427ff4c76e310f3c", "generation_seconds_batch": 21.017305470071733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19336746633052826, "target_z": 0.00048828031297351365, "ce": 6.141753673553467, "genuineness": 4.231201171875, "identity": 0.6285337209701538, "hypothesis": "De deur 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_Triumph/872b59ba244388bd7306be7670e8fdcb4b990ff853fd434e9045572b18b9d457.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "8742f53c102559c003dedc655314dce690c7beb5192a23a9b96c09a983be5705", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "03fdbf708137b97a6a80159e8113f4ccefe96dbca44f0a0becbe485462eee243", "generation_seconds_batch": 20.270679714041762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14902235567569733, "target_z": -0.08349610284466884, "ce": 6.372091293334961, "genuineness": 4.300237655639648, "identity": 0.19553901255130768, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8742f53c102559c003dedc655314dce690c7beb5192a23a9b96c09a983be5705.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "874667f83234a752c1b0a9f3ac25357bbeccd2aede82f856641d7c56402bbdf9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "250b55f9e822923724861066bcf419967226f0ccd94b9c73b755290f2668c094", "generation_seconds_batch": 19.47824438905809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11576353013515472, "target_z": -0.1464843761023841, "ce": 6.1894097328186035, "genuineness": 4.250029563903809, "identity": 0.25523462891578674, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/874667f83234a752c1b0a9f3ac25357bbeccd2aede82f856641d7c56402bbdf9.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "875f2394fc58a94cdc51242bf7b580a1d6ad658ec0c381b7b7af1ff848ecc5f6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9fbcb90a6632224ddab2f7b1fa3948f675837be63ff346cca457a0fa58ac92a", "generation_seconds_batch": 23.341752488981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.286956250667572, "target_z": 0.17773434435372198, "ce": 5.831989288330078, "genuineness": 3.4561104774475098, "identity": 0.41693705320358276, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/875f2394fc58a94cdc51242bf7b580a1d6ad658ec0c381b7b7af1ff848ecc5f6.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": "88bcfb8632f54d096241ae5d5f4550d973b36ca059484b67408683b7e4960736", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "104311f4c4181e6384316dc4b481de5fc6fe0d12ee59408f822ac54ed90dd492", "generation_seconds_batch": 21.609700013999827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47568076848983765, "target_z": 0.535156210755126, "ce": 6.125868320465088, "genuineness": 4.262581825256348, "identity": 0.5459522008895874, "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_Triumph/88bcfb8632f54d096241ae5d5f4550d973b36ca059484b67408683b7e4960736.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "8950e082ccb2bed84e3bf587046332429965c9614d241e8fddee6c0d70514df9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "07b6ba51607610b85cc06a2f4f46aa27dc9a0d315e9014ee536efb98cfbffe6c", "generation_seconds_batch": 20.41507291502785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33130139112472534, "target_z": 0.26171878395343035, "ce": 5.4666266441345215, "genuineness": 4.18726921081543, "identity": 0.5733941197395325, "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_Triumph/8950e082ccb2bed84e3bf587046332429965c9614d241e8fddee6c0d70514df9.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "897ff68eca7343eab2e81049d57e9a785217f4d6460651fe4ee55f7c6ea50342", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "efac8bd1ed571c06793d9f9db01789af398c4820809365a5d3d3a198bce9b39e", "generation_seconds_batch": 21.47745174402371, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44680488109588623, "target_z": 0.48046870281796045, "ce": 6.24500846862793, "genuineness": 4.482243061065674, "identity": 0.5695201754570007, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/897ff68eca7343eab2e81049d57e9a785217f4d6460651fe4ee55f7c6ea50342.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "898bceb1818925c5e31a71307ccabf8d863215ea61b101f1eb574619376deec9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "930755a8d3c80df2f045a52988a14288326734ddb77866c324d44b083f8eecc5", "generation_seconds_batch": 17.199481320916675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8991925716400146, "target_z": 5.125000296320846, "ce": 6.213237762451172, "genuineness": 4.13078498840332, "identity": 0.19119177758693695, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/898bceb1818925c5e31a71307ccabf8d863215ea61b101f1eb574619376deec9.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "89bf3fb13b9866cf3c31f9e69cb822d921a51fa7aa30bf0f4a9bf19d54721633", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7ac3739d72f43c8df1354639da856311f0a2b43963db375bf6a5a0109d70451c", "generation_seconds_batch": 14.890676548937336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.836629331111908, "target_z": 1.218750003527629, "ce": 5.8875885009765625, "genuineness": 3.747946262359619, "identity": 0.36519181728363037, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/89bf3fb13b9866cf3c31f9e69cb822d921a51fa7aa30bf0f4a9bf19d54721633.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "8a3cf04a652ef5f0ed1aff761eb8f2b6be59a3e0d604e6736635135fa0bf816e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "462a4d3b42ba1b14b95d064304af55e101fae34a85bbce1c6ce6e5050c802d0a", "generation_seconds_batch": 21.274803887004964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19053144752979279, "target_z": -0.0048828031297351365, "ce": 6.133810997009277, "genuineness": 3.9801597595214844, "identity": 0.23566576838493347, "hypothesis": "De deur 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_Triumph/8a3cf04a652ef5f0ed1aff761eb8f2b6be59a3e0d604e6736635135fa0bf816e.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "8ac92e7ba8dd84ee5750259a404c469831e1282ac97a011e349f80331c4dccf4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "69499aa5d41114de7ea9b22d79e4f78525a05f1924b93d27c5bfd12359d72b72", "generation_seconds_batch": 16.292830038932152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3728957176208496, "target_z": 2.2343749735427814, "ce": 6.372091293334961, "genuineness": 4.469690799713135, "identity": 0.675075888633728, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8ac92e7ba8dd84ee5750259a404c469831e1282ac97a011e349f80331c4dccf4.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "8ad0ef09bc0969557ea18e76d7be8a24a55a2ff5173734bb7abdfa61fc2f2ec3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1fb0d6cc4f6c48ee32a0bb8845982af45cbfeeb0aa7e2e5da5b1431319988e6b", "generation_seconds_batch": 24.07842190703377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28798753023147583, "target_z": 0.17968746560561602, "ce": 6.165581703186035, "genuineness": 4.337893962860107, "identity": 0.5815126895904541, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8ad0ef09bc0969557ea18e76d7be8a24a55a2ff5173734bb7abdfa61fc2f2ec3.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": "8ae993e1cd7ca83ccaaea3130a39ba6dc35f50a3ae627d30bea49bec84f37d3b", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "39c6352e5aba34e48dc7b11f86cc047a163d413a62c50bd806d2862500b4992a", "generation_seconds_batch": 18.101943789981306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38183414936065674, "target_z": 0.357421838180371, "ce": 6.213237762451172, "genuineness": 4.532451152801514, "identity": 0.8184087872505188, "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_Triumph/8ae993e1cd7ca83ccaaea3130a39ba6dc35f50a3ae627d30bea49bec84f37d3b.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "8afa92e872fe66d1de8cc42cadcf8da6660a68541bee86cf46cc1c495d8bbc77", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "13ae122ffe8e3b35b86a4e1db22c101e1c837c559d95eba929039e51fc327961", "generation_seconds_batch": 21.195551355020143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07966867834329605, "target_z": -0.21484374691332453, "ce": 6.038498878479004, "genuineness": 4.300237655639648, "identity": 0.6221194267272949, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8afa92e872fe66d1de8cc42cadcf8da6660a68541bee86cf46cc1c495d8bbc77.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "8b7dd55fe50acffeb45ead31705a86e09d880c0d7161adca3b4c25156c79f3e4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94af52c65ba3f1b025fc965ad38ed1e7b2053edfe0e11d6bea30386eea65ee8d", "generation_seconds_batch": 20.91279345494695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21425092220306396, "target_z": 0.04003907032692712, "ce": 6.038498878479004, "genuineness": 3.7793264389038086, "identity": 0.5823549628257751, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8b7dd55fe50acffeb45ead31705a86e09d880c0d7161adca3b4c25156c79f3e4.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": "8b834dd7c45dbc8a87d98654d53ef1aacd049ca2765abe972db2247b7a0424c8", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5e3e2cf1069e705d7fc82ff6f0dbbb28dc5b6ca7016a44001d3f759a4fff0bd", "generation_seconds_batch": 19.8739812100539, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19981297850608826, "target_z": 0.012695316358344356, "ce": 6.213237762451172, "genuineness": 4.231201171875, "identity": 0.374675452709198, "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_Triumph/8b834dd7c45dbc8a87d98654d53ef1aacd049ca2765abe972db2247b7a0424c8.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "8bc1f4daa28b4ded8604c60f765161f5633d7b8c9a02b82db5afc57dfb19df34", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ded525e9d7d76bf30a5d570a1ddf33f40e99830d15a340910ce4d0b254067f04", "generation_seconds_batch": 22.68229919602163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21064142882823944, "target_z": 0.03320311772426493, "ce": 6.221180438995361, "genuineness": 4.494794845581055, "identity": 0.5844262838363647, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8bc1f4daa28b4ded8604c60f765161f5633d7b8c9a02b82db5afc57dfb19df34.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": "8bdeaae5004fda7f39b6b82adb1971170f11989a4613fb899ebfdd476e2d4859", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "58b379276b6fff969c94e954303d7f34f7185917eac13534107e6b3d48d60759", "generation_seconds_batch": 17.90328684495762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14463941752910614, "target_z": -0.09179686816521856, "ce": 6.1894097328186035, "genuineness": 4.545003414154053, "identity": 0.7552645802497864, "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_Triumph/8bdeaae5004fda7f39b6b82adb1971170f11989a4613fb899ebfdd476e2d4859.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "8bf0b05048ca630e3b4c616c69b1b02318f65e6beda9b5003eb806b6db7a7b78", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "569b62091a42846d0475caf6853970bf48cc710ea4e7b5d4fc63575938bed356", "generation_seconds_batch": 20.674115338013507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4718987941741943, "target_z": 2.4218750652611387, "ce": 6.348263263702393, "genuineness": 4.306513786315918, "identity": 0.49267956614494324, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8bf0b05048ca630e3b4c616c69b1b02318f65e6beda9b5003eb806b6db7a7b78.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "8c146451e878aaff4c27c2ad050d8a51d47003b145d33dc930624b8e349e1fad", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "9cdb8a99d6af50f307e7997be9338dcc0b47a17c8e2c318cf87841c3cb2f739e", "generation_seconds_batch": 21.590925214928575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2986434698104858, "target_z": 2.0937500176381456, "ce": 5.974957466125488, "genuineness": 4.250029563903809, "identity": 0.6369175314903259, "hypothesis": "J'ai trouvé la 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_Triumph/8c146451e878aaff4c27c2ad050d8a51d47003b145d33dc930624b8e349e1fad.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "8c1fbd910ca595becb9d416b636d5c417799e08350acfd0e7eefc2a396ced809", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0c81c34e0aec4e2285906ba1cdd957c4847d76d1cc716ed70745a745bef66285", "generation_seconds_batch": 20.538122149999253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2622036933898926, "target_z": 5.812500331597138, "ce": 6.23706579208374, "genuineness": 4.017816066741943, "identity": 0.4038689136505127, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8c1fbd910ca595becb9d416b636d5c417799e08350acfd0e7eefc2a396ced809.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": "8c29be1ee180989eafaedda29bdd7ec4550b9f85e6be6e3b87bd94c33ba855fc", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9aed7efaa5a114488232687ccce7f1a660972c306db3fa3718d5f1bf08909ac", "generation_seconds_batch": 17.435959176975302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1253881454467773, "target_z": 1.7656249700151525, "ce": 6.403861999511719, "genuineness": 4.293961524963379, "identity": 0.5414993762969971, "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_Triumph/8c29be1ee180989eafaedda29bdd7ec4550b9f85e6be6e3b87bd94c33ba855fc.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "8d0be517b1ed2d21a704228c8230a13dfc8e78ca24c93d73634ad97b270b2f15", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "63d94399df1ba6c11b5532850c992979233640cb11224ec748b63bdf67d66298", "generation_seconds_batch": 22.65660486393608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.179701089859009, "target_z": 5.656250179909085, "ce": 6.308549880981445, "genuineness": 4.055472373962402, "identity": 0.2971920371055603, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8d0be517b1ed2d21a704228c8230a13dfc8e78ca24c93d73634ad97b270b2f15.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "8d0dbc4b310f8b0a051fbb1c0a15ba224219a07c9ef880b6e9a95fdbdc935d4f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "349410c9a82b2abd04b4bb0b88dbeabc181122d001cce479b9ceb208b8b94289", "generation_seconds_batch": 20.0103534309892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9397574663162231, "target_z": 1.4140624673694306, "ce": 6.038498878479004, "genuineness": 4.394378662109375, "identity": 0.6582915782928467, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8d0dbc4b310f8b0a051fbb1c0a15ba224219a07c9ef880b6e9a95fdbdc935d4f.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "8d35380bace145de331e7375cf9388933fc214bcf9d5a3f7e4ad88b374e66f5b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c0ee064a86e16b83263aa783534ddbc96b8c1271b16c270dad8ae6e273d559b4", "generation_seconds_batch": 20.65652687603142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6819370985031128, "target_z": 0.9257812513228609, "ce": 5.720792293548584, "genuineness": 3.9425034523010254, "identity": 0.6639652252197266, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8d35380bace145de331e7375cf9388933fc214bcf9d5a3f7e4ad88b374e66f5b.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "8dd58e5dd7b95eac2c0ad1a33878846ecda427dd0aca0cb4f6e5766aa7f886f3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f5afcb324932511eb4ceef77c9a02e2a8cc5ee6cb57ea3220347a0632c1f20cf", "generation_seconds_batch": 21.315680457046255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5066192150115967, "target_z": 0.5937499611960796, "ce": 5.879645347595215, "genuineness": 4.036643981933594, "identity": 0.7393597364425659, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/8dd58e5dd7b95eac2c0ad1a33878846ecda427dd0aca0cb4f6e5766aa7f886f3.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "8e2946169bba39c9c152857206b7d38fa294c0e7cd39d552bc403a78ead1fb4b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f8df0ec9bb0ea24c7bfd3ef86c9a6de23e8d298c58fde90c66365b27b22c9f4", "generation_seconds_batch": 21.664035146008246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0824174880981445, "target_z": 3.5781251040650592, "ce": 5.6254801750183105, "genuineness": 3.973883628845215, "identity": 0.5708729028701782, "hypothesis": "He encontrado la cajita, estaba junto, 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_Triumph/8e2946169bba39c9c152857206b7d38fa294c0e7cd39d552bc403a78ead1fb4b.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": "8efd145cf4240e2bfc05aa2bb312d3264718db623df64003f2cab1bc2faea6d8", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Escribí el número en el sobre.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b939e658863b9130e0da03c0c5523c115af65fcaf9a8ad4ed08281769e3a54a", "generation_seconds_batch": 14.598500501946546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8661916255950928, "target_z": 5.062500416260237, "ce": 5.824047088623047, "genuineness": 4.036643981933594, "identity": 0.529407799243927, "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_Triumph/8efd145cf4240e2bfc05aa2bb312d3264718db623df64003f2cab1bc2faea6d8.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "8f07ebadd7ac88e3c824bc6733915bbeeabf6bad91b7983242de66a6f9f72f34", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "812453cbc366c4d44ae60a2d263150d9f319af7e15dd4874f7988c314fd23826", "generation_seconds_batch": 21.63453281694092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9933841228485107, "target_z": 1.5156249982361854, "ce": 6.157639026641846, "genuineness": 4.337893962860107, "identity": 0.38379329442977905, "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_Triumph/8f07ebadd7ac88e3c824bc6733915bbeeabf6bad91b7983242de66a6f9f72f34.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": "902ac114d574993ab03029bc957c34b690d09a91924eb8274c5ce2d854ce0ee9", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "acc107360f159b5cb1f16a5e1f17047701ec05d2782821336d53fe2ff44ef6ad", "generation_seconds_batch": 17.823193632997572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07554355263710022, "target_z": -0.22265624603141723, "ce": 6.038498878479004, "genuineness": 4.105680465698242, "identity": 0.6755436062812805, "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_Triumph/902ac114d574993ab03029bc957c34b690d09a91924eb8274c5ce2d854ce0ee9.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": "90ea7f0dfce99025c6cc1e74e3865f859a4dbfb9e7cc6880ca6f8f274bbe26b7", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87c94966beb9cec36ae0457e72b94a8fa7a513dffa6ff95181401c9a4deaf9c0", "generation_seconds_batch": 18.982315207016654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10235687345266342, "target_z": -0.1718749947085563, "ce": 6.205295085906982, "genuineness": 4.017816066741943, "identity": 0.7684536576271057, "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_Triumph/90ea7f0dfce99025c6cc1e74e3865f859a4dbfb9e7cc6880ca6f8f274bbe26b7.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "91423d568c470fb4a729bfcb23f420d08470030d6f51585d6b62ba100c48479d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "035b462ad0bf55aa6f9aba4eadac9c6eabe7913ecaf49059fdc46468a23e4509", "generation_seconds_batch": 17.028998297988437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.394207715988159, "target_z": 6.062500303376105, "ce": 5.2918877601623535, "genuineness": 3.8295347690582275, "identity": 0.6902129650115967, "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_Triumph/91423d568c470fb4a729bfcb23f420d08470030d6f51585d6b62ba100c48479d.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "918a49e386d25ad5532396b5178a7b8540cf0e118590fbc60c6a639f64545621", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d930b2725dfa63d6a775ffbc02d76a11273150fa54452fda52a107f85bbf621", "generation_seconds_batch": 15.811354993027635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4306474924087524, "target_z": 2.3437499894171125, "ce": 6.268836498260498, "genuineness": 3.986435890197754, "identity": 0.5706040263175964, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/918a49e386d25ad5532396b5178a7b8540cf0e118590fbc60c6a639f64545621.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "91c942067010fae4814daa0004ba4650e8915d7ce6caeab0677041439ddacddb", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "03663b2aebdb49b5e285e724c326cf40b31765db4f5d363eff26e42f19ffb034", "generation_seconds_batch": 20.18757084594108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0987473875284195, "target_z": -0.178710933200702, "ce": 6.197352409362793, "genuineness": 4.645420074462891, "identity": 0.5238502025604248, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar tener 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_Triumph/91c942067010fae4814daa0004ba4650e8915d7ce6caeab0677041439ddacddb.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "91ecaa81a094c8ac970794e1966a7f2c69e67c9060a193061d19088bb2720322", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "50d38b816f720702c7c0b18f3ecd382a74665453a3361af88060292793198d5f", "generation_seconds_batch": 19.227986532030627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14928017556667328, "target_z": -0.08300782253169532, "ce": 6.213237762451172, "genuineness": 3.8797430992126465, "identity": 0.4400079846382141, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/91ecaa81a094c8ac970794e1966a7f2c69e67c9060a193061d19088bb2720322.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "92795c5dfd106059fe1129d2bf37cc4a89815030d5da53c3986d5bd36647d5cc", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e1b6bd26cae707ade488909ff3702cf49cebb01bdb409fe385b8e2ffe122d483", "generation_seconds_batch": 15.0303534490522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8761610984802246, "target_z": 3.1874999506131925, "ce": 6.086154937744141, "genuineness": 4.080576419830322, "identity": 0.49951088428497314, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/92795c5dfd106059fe1129d2bf37cc4a89815030d5da53c3986d5bd36647d5cc.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "92a65d1c755b68ef7075f4f1bf104fd11fd183c03745023d52f98165d3a5374c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b942d1b0eebc9e61191999a898364afeeae5a31ffe4449a3152bdf1481fe482d", "generation_seconds_batch": 14.883427757071331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7111560106277466, "target_z": 2.8749998730053514, "ce": 5.863759994506836, "genuineness": 3.9048471450805664, "identity": 0.6277117133140564, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/92a65d1c755b68ef7075f4f1bf104fd11fd183c03745023d52f98165d3a5374c.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "9313c26214286d14e4643364954b9493178284716b1fecd816c26e67323236d9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b9179ed583b5b18e7fba0fb1a2d90d13f47e7631fee2b9aab8e3408d8b4d0f03", "generation_seconds_batch": 19.3628157050116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7665021419525146, "target_z": 1.0859374197464373, "ce": 6.0305562019348145, "genuineness": 3.9801597595214844, "identity": 0.44932395219802856, "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_Triumph/9313c26214286d14e4643364954b9493178284716b1fecd816c26e67323236d9.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "937594b0b3ee87fd1d564ea62843db510a0936fabef4da5d2bc964157246f5f4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4737f4eb83dae3d3638dba3a4a9afe3e1e385420382ff7fa0865136126355161", "generation_seconds_batch": 19.890972580993548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9486939907073975, "target_z": 5.218750116411761, "ce": 5.927301406860352, "genuineness": 3.9048471450805664, "identity": 0.5003223419189453, "hypothesis": "J'ai trouvé la 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_Triumph/937594b0b3ee87fd1d564ea62843db510a0936fabef4da5d2bc964157246f5f4.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "946dda7a7ab0db72f5e69c8d1383db19ded39a1e1ac9710938886732a1320650", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "231735b9d4189c92e192d6f2ab1580908e8d40bfed490f573d60ec3931e53ad0", "generation_seconds_batch": 19.64174119499512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16500721871852875, "target_z": -0.05322266699824499, "ce": 5.990842819213867, "genuineness": 4.042920112609863, "identity": 0.6974667310714722, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/946dda7a7ab0db72f5e69c8d1383db19ded39a1e1ac9710938886732a1320650.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "947fd900b83b7bc23933e658fbd2f64ca9d6fba455b743cc329e0206a5919947", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "edecf5d6d2e519ac1d3d085ac1ca8cb050eaa9582d80b15051afb4ae445967ee", "generation_seconds_batch": 22.438804582925513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29365959763526917, "target_z": 0.19042968893309933, "ce": 5.816103935241699, "genuineness": 3.7667744159698486, "identity": 0.23260700702667236, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/947fd900b83b7bc23933e658fbd2f64ca9d6fba455b743cc329e0206a5919947.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": "94e25e778d18a62c006afdf6fb04e38f73d1f007afe8adf4fe40b9537a7b2dfa", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8cf678bb2394835da925a41f7de10dd9d9fdac75e4f4e96783a3a0a4bedf01b3", "generation_seconds_batch": 16.89781374996528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09204405546188354, "target_z": -0.19140624955904637, "ce": 6.038498878479004, "genuineness": 4.093128204345703, "identity": 0.4491645097732544, "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_Triumph/94e25e778d18a62c006afdf6fb04e38f73d1f007afe8adf4fe40b9537a7b2dfa.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "9510779fd6bf27c03384fb44c37f0eb6d499ab7ee9250223c41c33d47ce2bb8d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "47501fc806cfe3d1a803a85dd257c9ab4617623c608d0ae5c59e25ec11fa6f5a", "generation_seconds_batch": 19.49327563296538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.737626314163208, "target_z": 1.0312500246934038, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.6620946526527405, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9510779fd6bf27c03384fb44c37f0eb6d499ab7ee9250223c41c33d47ce2bb8d.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": "95d2306e404ab5084ba50ad2225db790f6a93b3d123a70ab1a3f78a645858a45", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The keys are on the kitchen table.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ac8da43e6607e22b756e3ac2984a55deed12a814477580bddfa9a7c6c71d766", "generation_seconds_batch": 21.281649257987738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09668482095003128, "target_z": -0.1826171898150066, "ce": 6.395919322967529, "genuineness": 4.331617832183838, "identity": 0.43820327520370483, "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_Triumph/95d2306e404ab5084ba50ad2225db790f6a93b3d123a70ab1a3f78a645858a45.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "95d5830638f0cb4ea7d7af56b7a4d83053da3a1220f882424760b6437127cfb8", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d2dc525bf30d8b5fb0fae68738869b2981ce9db73089e0259e8513dfaf13fd35", "generation_seconds_batch": 21.315680457046255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0494165420532227, "target_z": 3.5156252240044497, "ce": 5.708878040313721, "genuineness": 3.9299514293670654, "identity": 0.6113417148590088, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/95d5830638f0cb4ea7d7af56b7a4d83053da3a1220f882424760b6437127cfb8.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "96a64255c0836c704b9b7d6d5aa1e5fdf575af42f5676e2a814914b907fe45f9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fdaf8593f067ac1cf567f1e44c5b597c9d8201dfc414f0ff65d992dbf09bffed", "generation_seconds_batch": 21.288842648034915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.437178373336792, "target_z": 4.250000169326198, "ce": 5.569881439208984, "genuineness": 4.005263805389404, "identity": 0.5500421524047852, "hypothesis": "J'ai trouvé la petite boîte ! Elle était près de la vieille fenêtre ! Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/96a64255c0836c704b9b7d6d5aa1e5fdf575af42f5676e2a814914b907fe45f9.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "96f304dfa8e222fd78612db9ac96a9c381a380fa462d339e8725518bacc2385c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "604f6e79e839154d380fb608e455f2b43455ebf171f8fcc59818388226d205cc", "generation_seconds_batch": 20.073796384967864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38080286979675293, "target_z": 0.355468716928477, "ce": 5.855817794799805, "genuineness": 3.7040140628814697, "identity": 0.30917873978614807, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/96f304dfa8e222fd78612db9ac96a9c381a380fa462d339e8725518bacc2385c.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "96f85a669b8ac599dd26da0a0fc20aa531669631fd140f29703bd4f7720c1f86", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "aadd660bd18d94a07aec0fbcbd83a653f06cf5a181d7c9f4d3a60d1f63612292", "generation_seconds_batch": 21.91700855595991, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19775041937828064, "target_z": 0.008789073854556247, "ce": 5.95112943649292, "genuineness": 4.331617832183838, "identity": 0.6957601308822632, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/96f85a669b8ac599dd26da0a0fc20aa531669631fd140f29703bd4f7720c1f86.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "973f6f432d59dbd68307e1b39e625fe3c7737b190f203ddabd5126c8ace06508", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "35b9955c676dc2938306be16c2dd48f98f2f4855be1c0cf4669ac671160eb064", "generation_seconds_batch": 17.33960297401063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3416141867637634, "target_z": 0.28124999647237087, "ce": 6.1020402908325195, "genuineness": 4.162164688110352, "identity": 0.40672892332077026, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/973f6f432d59dbd68307e1b39e625fe3c7737b190f203ddabd5126c8ace06508.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": "9752c387cbc7f37f3deab98f439d075012aae06f965f1ae097becc0ea909b991", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c30a8d1d2aafe6b98b7fafad18bc7b811fae228ef8dce65a262cda3929edb1d", "generation_seconds_batch": 19.111468471004628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7995032072067261, "target_z": 1.1484375255753112, "ce": 6.300607204437256, "genuineness": 3.898571252822876, "identity": 0.5074635744094849, "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_Triumph/9752c387cbc7f37f3deab98f439d075012aae06f965f1ae097becc0ea909b991.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "97d7767a00028e333d219a98727864ee6b2f455dad8cade7be0bdf5e7cf69a4d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "24bab737ab8d81d8a7183b0a1600379a14b726c7091a591f1b069b9993745068", "generation_seconds_batch": 20.382748274016194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4801490306854248, "target_z": 2.437500035276291, "ce": 5.824047088623047, "genuineness": 4.042920112609863, "identity": 0.4067207872867584, "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_Triumph/97d7767a00028e333d219a98727864ee6b2f455dad8cade7be0bdf5e7cf69a4d.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "2f4689882f89de9d691dc4eb0109e4a96751f665ce0658a10977b4c9dc9b9986", "generation_seconds_batch": 14.984395907027647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07502791285514832, "target_z": -0.22363280665736426, "ce": 6.4912309646606445, "genuineness": 4.720732688903809, "identity": 0.577409029006958, "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_Triumph/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "99e4c6ceda9c119627c688ea81c705ca0fccb78c086a9bad961e6ad092896b99", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "95373de2dd082b1d5269c1c0ffd9ad4e9eace357e17cec4ad1c88c991af1d7d2", "generation_seconds_batch": 20.991633152007125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5210571885108948, "target_z": 0.6210937716067284, "ce": 6.252951145172119, "genuineness": 4.256305694580078, "identity": 0.5967499017715454, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/99e4c6ceda9c119627c688ea81c705ca0fccb78c086a9bad961e6ad092896b99.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "9ad4b2f9a22fac367f2580c59a907069e77a24816fd32851d7e13425c6f0554c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b545b206e327bc4e6e480ac0d48d364a347c579909b35a0c476e4fb4621f7dbf", "generation_seconds_batch": 20.800783648970537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1309749335050583, "target_z": -0.1176757811948808, "ce": 6.197352409362793, "genuineness": 4.482243061065674, "identity": 0.6646370887756348, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9ad4b2f9a22fac367f2580c59a907069e77a24816fd32851d7e13425c6f0554c.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "9af2bb26c30b1e23f93698d1091715653de282ee54649fc0ba3f4ea47ac0c248", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b0bcffee02e53b5a4cd580b89b74dfed319898fecfc219d617be1d5bde4c607", "generation_seconds_batch": 22.45248657197226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0016343593597412, "target_z": 1.5312499682513379, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.6645662188529968, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9af2bb26c30b1e23f93698d1091715653de282ee54649fc0ba3f4ea47ac0c248.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "9b09ed0ee1bb9bd4dfaa60c7ae94b56fd6530faf574f5f637dc815fab5c3b52a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8b225ccc26f183dbf1ee7b3066c510478df7e3256ed4a5216f0833d4d83c055c", "generation_seconds_batch": 19.387413332005963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7500016689300537, "target_z": 1.0546874797161325, "ce": 6.284721851348877, "genuineness": 4.595211505889893, "identity": 0.640661895275116, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9b09ed0ee1bb9bd4dfaa60c7ae94b56fd6530faf574f5f637dc815fab5c3b52a.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": "9b565d68599062a236bab292554c8149d134516fb7295c55d944837cb9f76efe", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1571e5e4c1cce85c22e14d49cdfa5b5716d7ea82d730fd30c3d7b36547ea2628", "generation_seconds_batch": 17.248792842030525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06523074209690094, "target_z": -0.2421874867713908, "ce": 6.2767791748046875, "genuineness": 4.444586753845215, "identity": 0.6022579073905945, "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_Triumph/9b565d68599062a236bab292554c8149d134516fb7295c55d944837cb9f76efe.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "9bd98c0e3860d4700516fe601316d95ae4c3c18102ec0d9c1ce93f7e4a294c92", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1cc00d415cfd1e5823d11a8dc9f7dcdc881ea3abe8d237e8232e54afefd6992b", "generation_seconds_batch": 14.853941571083851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06935586035251617, "target_z": -0.23437500176381457, "ce": 6.356205940246582, "genuineness": 4.419482707977295, "identity": 0.6608484983444214, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9bd98c0e3860d4700516fe601316d95ae4c3c18102ec0d9c1ce93f7e4a294c92.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "f33fea61a1f1bba0b49d3c349ead883a5542e81fd8abffba9bc12dbaf8418d4e", "generation_seconds_batch": 14.82149106496945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06574638187885284, "target_z": -0.24121092614544376, "ce": 6.23706579208374, "genuineness": 4.432034492492676, "identity": 0.6185101270675659, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier, naast de hoge moekenkast. We zetten het na de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.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": "9c5222a4c1186f2801a25522936bf6fb7d586a5b1bc74b61cd11e38c5892dd33", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "abde96ba3d4e68a3b894961cf8c6e21872770f93ac5bd46658448052f2127e65", "generation_seconds_batch": 14.720007871976122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5107443332672119, "target_z": 0.6015624462036558, "ce": 5.80021858215332, "genuineness": 4.042920112609863, "identity": 0.49371522665023804, "hypothesis": "Las llaves están en la mesa de la cocina. Mire en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9c5222a4c1186f2801a25522936bf6fb7d586a5b1bc74b61cd11e38c5892dd33.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "9c5406a634c1a67ec7f3d9cc6d254656dd709db4e97cad3510e9e87b7281a367", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3f54a6614af06e4fd728da2089c8c536c0f25ea30e416dd2008d0ae5938b4ad2", "generation_seconds_batch": 21.13251196302008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3447060585021973, "target_z": 5.968750031748662, "ce": 5.720792293548584, "genuineness": 3.9927117824554443, "identity": 0.30452054738998413, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9c5406a634c1a67ec7f3d9cc6d254656dd709db4e97cad3510e9e87b7281a367.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "7f6d7a51bd680ac6c6198812a0875faa4a4fda1951b3a49110fb2326865ea84d", "generation_seconds_batch": 15.827961358940229, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04873022437095642, "target_z": -0.27343751146479467, "ce": 6.205295085906982, "genuineness": 4.017816066741943, "identity": 0.6101723909378052, "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_Triumph/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "9d514f05e26f2df507e3065cbd6f96a5e39fc8f4c7e77e43c5483063a8eb0753", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "78f0d03d0380a5598e72c7314b60d8549e1cf41d54bfd084cf313115cb7ab7e3", "generation_seconds_batch": 21.687121305032633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3137695789337158, "target_z": 0.2285156097870994, "ce": 5.998785495758057, "genuineness": 4.080576419830322, "identity": 0.5242810249328613, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9d514f05e26f2df507e3065cbd6f96a5e39fc8f4c7e77e43c5483063a8eb0753.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "9d68f8524f5c6825688ed7afb934cc1dc4c9a5e3b5ba935b2eba0c03791e7036", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a7bf500ec660e5c1184f9023a7e8e07f1477fb705626648ca98efec2d21d5fdc", "generation_seconds_batch": 21.94802279805299, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6186840534210205, "target_z": 4.593750412732607, "ce": 5.7247633934021, "genuineness": 3.8797430992126465, "identity": 0.2960098683834076, "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_Triumph/9d68f8524f5c6825688ed7afb934cc1dc4c9a5e3b5ba935b2eba0c03791e7036.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "9d8f901a6385b3c5e2e212d2f14aff8f2fc17f13e5891bb838697f458c5f90ae", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "38702e135365df185b219f653e991b94e79f2665738d604e91fed4a83932bef9", "generation_seconds_batch": 15.298808315885253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27922165393829346, "target_z": 0.16308593496451657, "ce": 6.1020402908325195, "genuineness": 4.068024158477783, "identity": 0.7796313166618347, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9d8f901a6385b3c5e2e212d2f14aff8f2fc17f13e5891bb838697f458c5f90ae.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": "9d903cbf15a282386a84c1b14ba840b3f9e0bc024025a076717c1ea18471d14a", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a649ec213743bd427f014dcdb0f27c3874100d9eb80ffb9bfd611d518404dc68", "generation_seconds_batch": 14.877552654943429, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1955152750015259, "target_z": 1.8984374409122122, "ce": 6.006728172302246, "genuineness": 4.432034492492676, "identity": 0.6171570420265198, "hypothesis": "Quelqu'un a dit placé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9d903cbf15a282386a84c1b14ba840b3f9e0bc024025a076717c1ea18471d14a.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": "9db6b9322c6cae2cc9365b417e92f5b26174ae9303e8a3cc6e9c70b8cda79fde", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I wrote the number on the envelope.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45bc1ecbce4cf8224c48775517ffa76265d3020a089b8e1460dc4e87a439b57b", "generation_seconds_batch": 16.078394017997198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3381752967834473, "target_z": 4.062500077607841, "ce": 5.967014789581299, "genuineness": 3.5439748764038086, "identity": 0.42263883352279663, "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_Triumph/9db6b9322c6cae2cc9365b417e92f5b26174ae9303e8a3cc6e9c70b8cda79fde.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "9ddfb6e9e484cf6f2a04ee469e65125a50de0f6854757287fd33ade2499af78e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1c50a011acff0f7b197f1b46cc6015259c8618332d2bdad4e1ef8e95102e25fc", "generation_seconds_batch": 21.840600966941565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5856828689575195, "target_z": 4.53125008113547, "ce": 6.356205940246582, "genuineness": 3.9299514293670654, "identity": 0.49007946252822876, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9ddfb6e9e484cf6f2a04ee469e65125a50de0f6854757287fd33ade2499af78e.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "9e0e627daba78de00b95dbe3bce5e42069f4d0a0fee93208056266f11c57054a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "355c86bd460a7cabc0d57811c2d180ba76cdb4d67b7e9a4753c60a045c388ae7", "generation_seconds_batch": 19.297856950899586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16113992035388947, "target_z": -0.0605468716928477, "ce": 6.1894097328186035, "genuineness": 4.099404335021973, "identity": 0.4140183925628662, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9e0e627daba78de00b95dbe3bce5e42069f4d0a0fee93208056266f11c57054a.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "9e64d0f742f2bbaa9623a8fa7740ef1f2e6df1dbb7d8bf70c101a557245d7021", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "27c44eb4ea1330752535c48c70085b78514cd38fcb589023e6a76ac514b60bce", "generation_seconds_batch": 22.422023644088767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8902559280395508, "target_z": 1.320312421510252, "ce": 6.062326908111572, "genuineness": 4.005263805389404, "identity": 0.5312204957008362, "hypothesis": "Uh I found a little box! It was beside the old window. We can look inside together!", "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_Triumph/9e64d0f742f2bbaa9623a8fa7740ef1f2e6df1dbb7d8bf70c101a557245d7021.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "9ecab77fe8655540bbcf76498d096907b0be510d10bbb3c146a0453d7394d017", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "42a604eda01318a7bce04d04c5a47191a8534d184f51cc4a60bdab7a9ee3a7cf", "generation_seconds_batch": 19.325065540033393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09049713611602783, "target_z": -0.19433593143688743, "ce": 6.221180438995361, "genuineness": 4.7081804275512695, "identity": 0.7388161420822144, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9ecab77fe8655540bbcf76498d096907b0be510d10bbb3c146a0453d7394d017.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "9f90e6bd472371756c74d903526c157523135222f1090596661a049f1024ccab", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "07fcd5b029ed8eaa166643c60c53744e2c073662210c95c36928936e6674e9a0", "generation_seconds_batch": 21.08815476996824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19182054698467255, "target_z": -0.0024414015648675682, "ce": 6.181467056274414, "genuineness": 4.406930446624756, "identity": 0.5378506779670715, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9f90e6bd472371756c74d903526c157523135222f1090596661a049f1024ccab.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "9f9edcf278d5d58bc7bb1715af0f6aa1a563230ff80685b40635e428da60169a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8b7a8097549e5c38ddd1f0a7e51047228847f47179c122d36877ab3c35242ea1", "generation_seconds_batch": 14.88913283299189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46330541372299194, "target_z": 0.5117187557323973, "ce": 6.046441555023193, "genuineness": 4.570107460021973, "identity": 0.6784845590591431, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9f9edcf278d5d58bc7bb1715af0f6aa1a563230ff80685b40635e428da60169a.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "9fbfb5efe1ab75b6089ce7b163b5d707ffd26f6a4a6d33b6f17b935c767b9d9f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "939b990a11f5b40d3f283515b4067e4cb3d3d79297050ebc0bb7340e3c10e9a5", "generation_seconds_batch": 19.69986935693305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1598508208990097, "target_z": -0.06298827325771526, "ce": 6.165581703186035, "genuineness": 4.143336772918701, "identity": 0.7184621095657349, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/9fbfb5efe1ab75b6089ce7b163b5d707ffd26f6a4a6d33b6f17b935c767b9d9f.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": "9fc7dab0cb9a18b0aa4bce06b9d284a52d97d957f47208b4be3f908158cfff66", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "56ded4b34938792903a2b762150b836e977915b7ac6be670c65fc8e9dead0113", "generation_seconds_batch": 20.127858270076104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5354951024055481, "target_z": 0.6484374691332452, "ce": 6.205295085906982, "genuineness": 4.469690799713135, "identity": 0.6909911632537842, "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_Triumph/9fc7dab0cb9a18b0aa4bce06b9d284a52d97d957f47208b4be3f908158cfff66.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "a06ae560c6d64e26e96256c64c2e11b77af808ca32cf5aa797823f45613a96de", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cbf20ffcdad31a5393af0ac6a0ba991ce3a265f0c66793e4814d8734d798676e", "generation_seconds_batch": 20.80737048201263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3051743507385254, "target_z": 4.000000197547231, "ce": 5.7247633934021, "genuineness": 4.118232727050781, "identity": 0.6062030792236328, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a06ae560c6d64e26e96256c64c2e11b77af808ca32cf5aa797823f45613a96de.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "a09d21dd7a2d4009cd661bc6b0570ed098e8194657ded72b956335b2aabd327a", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d6463e798106c13360059c389d94503032e58b16ed991b119695ceaa7acc0ba1", "generation_seconds_batch": 15.109354506013915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11988865584135056, "target_z": -0.13867187698429137, "ce": 5.550024509429932, "genuineness": 3.7542223930358887, "identity": 0.3543255925178528, "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_Triumph/a09d21dd7a2d4009cd661bc6b0570ed098e8194657ded72b956335b2aabd327a.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": "a0b9e2f1663dfd7178e86dcfba5eaf282dfb9e3f460205a709908dc7314974d2", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fab7f206823be176b98dba3adab83cc70c9c4462ca9d6f0a36603d49c208f265", "generation_seconds_batch": 19.667238306021318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08069995790719986, "target_z": -0.21289062566143047, "ce": 6.4515180587768555, "genuineness": 4.469690799713135, "identity": 0.40546226501464844, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter, bis zum kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a0b9e2f1663dfd7178e86dcfba5eaf282dfb9e3f460205a709908dc7314974d2.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "a2e19905fb2041d0a830d07789ef687979ce69e8cbc29100f6f9392df0ffb01f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e24d7305f96857704588007666a989f2e502d1c0274e97ac6ea4bfea99e70495", "generation_seconds_batch": 21.840600966941565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.816689968109131, "target_z": 4.968750144632794, "ce": 6.23706579208374, "genuineness": 4.055472373962402, "identity": 0.4934981167316437, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a2e19905fb2041d0a830d07789ef687979ce69e8cbc29100f6f9392df0ffb01f.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "a3054b1d2cb18c59dd703c4ea0561cbccfcca2299aed78fdd7ecc677d620e9c4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9c6388e74c5e09977cdfc6ec677af779635e53abac83cf9db372cf62c6fa9049", "generation_seconds_batch": 19.383336017024703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24802538752555847, "target_z": 0.10400390421058942, "ce": 5.855817794799805, "genuineness": 4.017816066741943, "identity": 0.46741199493408203, "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_Triumph/a3054b1d2cb18c59dd703c4ea0561cbccfcca2299aed78fdd7ecc677d620e9c4.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "a3865fee345f39316e4e50f1af3e7424269dc4421d2be1524a5e8aa7dfceab44", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0714fec9f27673eb67e0fc2f3bade80579290757e647f4dd38e6a9ca4fb4d269", "generation_seconds_batch": 21.52521689608693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6056222915649414, "target_z": 0.7812500529144368, "ce": 6.268836498260498, "genuineness": 4.494794845581055, "identity": 0.30844569206237793, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a3865fee345f39316e4e50f1af3e7424269dc4421d2be1524a5e8aa7dfceab44.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "a3976017e5f3cc6a320c1d0b79a0a68431e6c85709b68c880366e437755f8b8e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "03109d2202a6af02b0bde068b4c1a1ae683d0fd378158990222f39f585f6977c", "generation_seconds_batch": 21.241924621979706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2986434698104858, "target_z": 2.0937500176381456, "ce": 6.141753673553467, "genuineness": 4.20609712600708, "identity": 0.5367788076400757, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a3976017e5f3cc6a320c1d0b79a0a68431e6c85709b68c880366e437755f8b8e.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "a3cdb84777269c21d0fc24d2e20f5dffd32c751e6c821803d1e7544143ced879", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "46077c64cfd871f69e7253b4785b0206959074b7e7b54bfd8335d7715ea2d3f3", "generation_seconds_batch": 19.383336017024703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31995725631713867, "target_z": 0.24023433729846372, "ce": 5.847874641418457, "genuineness": 4.080576419830322, "identity": 0.4567067325115204, "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_Triumph/a3cdb84777269c21d0fc24d2e20f5dffd32c751e6c821803d1e7544143ced879.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": "a464a16b31ef58b50d7a1fc98ce320327a6cb5d6e51467064239cfbfc026ac40", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "db7e5d61ff53b33319a6570b8b07dc392fb65b8a0c55bb7e23c17d470ae61927", "generation_seconds_batch": 15.664619317045435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.282142996788025, "target_z": 2.0625000776078406, "ce": 6.157639026641846, "genuineness": 4.293961524963379, "identity": 0.19306859374046326, "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_Triumph/a464a16b31ef58b50d7a1fc98ce320327a6cb5d6e51467064239cfbfc026ac40.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": "a4ad284159a3e7c7a726dd114d878f55391e80b0cdd745827c6bb03e65fae439", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cce6cc60a0ef2e2072ae50eab8520cc4bb202d2594bd091440f262373bd928c9", "generation_seconds_batch": 20.353582159033976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4141470193862915, "target_z": 2.3125000493868075, "ce": 6.157639026641846, "genuineness": 4.086852550506592, "identity": 0.4941959083080292, "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_Triumph/a4ad284159a3e7c7a726dd114d878f55391e80b0cdd745827c6bb03e65fae439.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "a4d3a65c360eb4d3f8a235859258d9b5beee24ea9c4986f0f5477ba919d57ffe", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "605d7dbf0996a9c2745d9f1734eaeba08f3523957515d0bd2e257292a7f1a4d2", "generation_seconds_batch": 15.85813246993348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.494243860244751, "target_z": 0.5703125061733509, "ce": 5.998785495758057, "genuineness": 3.936227321624756, "identity": 0.2139265239238739, "hypothesis": "De deur 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_Triumph/a4d3a65c360eb4d3f8a235859258d9b5beee24ea9c4986f0f5477ba919d57ffe.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "a4de8fc259b0603a4cd1f31e294d65b0abcfeea40390eee2fbfa1d780e6018ef", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6fab34b8d5717d1c890115272d65d36aad0808d9ba4fb437635420fee35715d2", "generation_seconds_batch": 19.166989169083536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2730339765548706, "target_z": 0.15136720745315224, "ce": 6.340320587158203, "genuineness": 4.20609712600708, "identity": 0.37684184312820435, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a4de8fc259b0603a4cd1f31e294d65b0abcfeea40390eee2fbfa1d780e6018ef.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "a4e04c68808081ae24a381de194665073896e74ebec89dd96ede819b71a1658d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "effdb7cf8e52638faab7e83ce17ba84dd2e17ecdde33caf5353913a772a344b1", "generation_seconds_batch": 19.263623476028442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.503180503845215, "target_z": 4.375000380983946, "ce": 6.403861999511719, "genuineness": 4.174716949462891, "identity": 0.4843251705169678, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a4e04c68808081ae24a381de194665073896e74ebec89dd96ede819b71a1658d.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "a5d4f9b94d7ccac14c1f36625f8c7fd9046e877d0bb08949590bd2f320e4da19", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4ad2b2a4814862dcff2bcc18e2219570519ffe2128646e637495530100bbcf61", "generation_seconds_batch": 20.270679714041762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1448972374200821, "target_z": -0.09130858785224506, "ce": 6.268836498260498, "genuineness": 4.143336772918701, "identity": 0.29552602767944336, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a5d4f9b94d7ccac14c1f36625f8c7fd9046e877d0bb08949590bd2f320e4da19.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "a6f4c59fb1d494c87a14b56ae76f5bd0699be66b718e39fc86bd1ba9e8533675", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "24d72c97e0acc56bb05f63d39c8b334641af006e5fd4faef155e3089d21ad801", "generation_seconds_batch": 21.017305470071733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18846887350082397, "target_z": -0.008789073854556247, "ce": 6.268836498260498, "genuineness": 4.21237325668335, "identity": 0.756130039691925, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a6f4c59fb1d494c87a14b56ae76f5bd0699be66b718e39fc86bd1ba9e8533675.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "a717ef19ffb562709b8d25e25fcfbf24971cfae0d1b15bf6bd99b13f76d815dd", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0bfee35d1f3801900e67c07d2a63a305c4f1e6ad4f430a2828b92a79ab152984", "generation_seconds_batch": 21.669141376041807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11163840442895889, "target_z": -0.15429687522047683, "ce": 6.229123115539551, "genuineness": 3.810706615447998, "identity": 0.33475857973098755, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a717ef19ffb562709b8d25e25fcfbf24971cfae0d1b15bf6bd99b13f76d815dd.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "a7632b413d89d26dc5a8324d7c34457164c5ead3f5bb210e760edb90020c5695", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e654fecd459918157f6af786f911181d48ed3f416944afba0b6aa0b16061278b", "generation_seconds_batch": 20.734853558940813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26323679089546204, "target_z": 0.13281249911809273, "ce": 6.141753673553467, "genuineness": 4.507347106933594, "identity": 0.6690393090248108, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a7632b413d89d26dc5a8324d7c34457164c5ead3f5bb210e760edb90020c5695.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "a78254fa11542c09940d3b675b20feaeb4ef4092709b33ca9a8fd508792cc948", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a58806c1613e601c5e8af8364dd321a5bea1fac6af18479711d884c160c3e679", "generation_seconds_batch": 17.747232232941315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.225852832198143, "target_z": 0.06201171263176824, "ce": 6.0305562019348145, "genuineness": 4.011539936065674, "identity": 0.3929980993270874, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a78254fa11542c09940d3b675b20feaeb4ef4092709b33ca9a8fd508792cc948.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "a7bdb1ca9fc93ad9693ad219dd5c9ceae664f45f8dd2b1be2b19a415f7b8a601", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4d4cd52d991f422544a6f5d3c807a612a78b09d4b4c106b5e8fcf8ef3b19a70b", "generation_seconds_batch": 19.733593913028017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6406858563423157, "target_z": 0.8476562883629667, "ce": 6.292664527893066, "genuineness": 4.168440818786621, "identity": 0.5304738283157349, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a7bdb1ca9fc93ad9693ad219dd5c9ceae664f45f8dd2b1be2b19a415f7b8a601.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "a7c7d95690ef3ef8476794dbdc09856eb206cf722264a1304f8530ec49bf798a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "397c9d5b7a0dfad5f78a52d423a53099b3511947be9638379bcde92eb7d3eb21", "generation_seconds_batch": 22.19570771092549, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.546151041984558, "target_z": 2.562500021165775, "ce": 5.518253803253174, "genuineness": 3.9173994064331055, "identity": 0.4517437517642975, "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_Triumph/a7c7d95690ef3ef8476794dbdc09856eb206cf722264a1304f8530ec49bf798a.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "a7c99a84d19b1be0542e6cb7f0ac8f2ea571f854bcd4a52e03fe028a5d1dc3c3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e368aabbf29300200a1d5bf0a15d3aa3f3fdeb237b2a7906e0532beaa7d0d41", "generation_seconds_batch": 22.029653492965735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9191318154335022, "target_z": 1.3749999294474176, "ce": 6.09409761428833, "genuineness": 4.011539936065674, "identity": 0.4138186573982239, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a7c99a84d19b1be0542e6cb7f0ac8f2ea571f854bcd4a52e03fe028a5d1dc3c3.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": "a7d39987f2b0b44d4353b541bbfd9872163c3cafd65d70674edf8bff90bfd718", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6fc278325a1317165326bff14b6159c1d1252dc72003f445e0aa0a73819e9d14", "generation_seconds_batch": 18.976227204082534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12040429562330246, "target_z": -0.13769531635834437, "ce": 6.38003396987915, "genuineness": 4.406930446624756, "identity": 0.4135570526123047, "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_Triumph/a7d39987f2b0b44d4353b541bbfd9872163c3cafd65d70674edf8bff90bfd718.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "c892994991d414cd65555706166253415dd7126e2ca118f06a69a38d27eea027", "generation_seconds_batch": 14.816853134892881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04769894480705261, "target_z": -0.27539063271668873, "ce": 6.205295085906982, "genuineness": 4.3881025314331055, "identity": 0.703604519367218, "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_Triumph/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "a90953be0d88c2ddb106f2400673dfb9169462321949eead0e1eb09989c6dc5c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4f48651855058a75c0150b852cbec6f61bcf24eb0bb43b37111da68dcf78f50d", "generation_seconds_batch": 14.393736129975878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6451539993286133, "target_z": 2.749999887115868, "ce": 5.502368927001953, "genuineness": 4.080576419830322, "identity": 0.364024817943573, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a90953be0d88c2ddb106f2400673dfb9169462321949eead0e1eb09989c6dc5c.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": "a9125a921940d45ba87d9c3b5fce170887eb8ad986ee7d149c5ef1f902aea3a7", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Someone moved the little blue chair.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "901237308e1485c6337cd1243283805cb3ee7365d29416afeae789e208c1c5a4", "generation_seconds_batch": 15.546806226950139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20032861828804016, "target_z": 0.013671876984291382, "ce": 6.149696350097656, "genuineness": 4.105680465698242, "identity": 0.6454598903656006, "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_Triumph/a9125a921940d45ba87d9c3b5fce170887eb8ad986ee7d149c5ef1f902aea3a7.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "a9266ccc71df5bd44514f1db1c3066e6ac833fb2c4256a6e28acb743ca009ffd", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "15e8eca0489350312886ba17ef1e1145dcf6a005cea99c20ae71099ffbafacfc", "generation_seconds_batch": 22.54306119401008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.294690877199173, "target_z": 0.1923828101849934, "ce": 5.967014789581299, "genuineness": 3.773050308227539, "identity": 0.37162327766418457, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a9266ccc71df5bd44514f1db1c3066e6ac833fb2c4256a6e28acb743ca009ffd.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "a92a5b76dc7600c5e2094f2317953645e5806bad1cb31e3b1d4642524adf5796", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1d8798c15740624b7b013114d6a0bca1d20c2f4fe9ce5e86efa63e8d86b252e9", "generation_seconds_batch": 14.393736129975878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2450168132781982, "target_z": 1.9921874867713907, "ce": 5.935244083404541, "genuineness": 4.080576419830322, "identity": 0.5985137820243835, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a92a5b76dc7600c5e2094f2317953645e5806bad1cb31e3b1d4642524adf5796.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "4319ce50aabb9aac1c77c9d3027965e9256d605d4a7507d73c83d4f6341c8a9b", "generation_seconds_batch": 17.046033245977014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06574638187885284, "target_z": -0.24121092614544376, "ce": 6.141753673553467, "genuineness": 4.381826400756836, "identity": 0.7705218195915222, "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_Triumph/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.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": "a9dcb4784a7afc0fb566f7b515b1d5e0bc093fdba85be4ed14e85e3c9b0fcd29", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d6adb2953795334aa3b9660debdd671657ae6865a497863c351af4743a1eefa0", "generation_seconds_batch": 19.923370825941674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8737554550170898, "target_z": 1.2890624814799472, "ce": 6.268836498260498, "genuineness": 4.632867813110352, "identity": 0.6015440225601196, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand il auras un moment.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/a9dcb4784a7afc0fb566f7b515b1d5e0bc093fdba85be4ed14e85e3c9b0fcd29.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "aa6ff9c9d6c696c4b9111f03a1bc76b326b28f589a535e547977649b448bc2de", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6226b05aef9975c43b1023984e1157b52871b8e68d2179c446e56b47194213a0", "generation_seconds_batch": 23.418902350007556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2391722202301025, "target_z": 3.8749999858894837, "ce": 5.804190158843994, "genuineness": 4.231201171875, "identity": 0.5692209601402283, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre ! Nous pouvons regarder ensemble ce qu'elle contient !", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/aa6ff9c9d6c696c4b9111f03a1bc76b326b28f589a535e547977649b448bc2de.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "ab0084cfea3dc15be69a4cebd1d3145b590e605d540cc92dc1d1d9429a2d793d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "51ff775ff5d5dbe9fc781bd90a79425e85a498cc377587a55663b5e3eb4461c0", "generation_seconds_batch": 19.96164101199247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.397646427154541, "target_z": 2.281249883588239, "ce": 5.982900142669678, "genuineness": 4.086852550506592, "identity": 0.6513286828994751, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ab0084cfea3dc15be69a4cebd1d3145b590e605d540cc92dc1d1d9429a2d793d.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "ab14b25c1f3bbb6d3006827e9b11c6fa51153ffc72406061faff69961cb4ae9b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dffb3e5fb94ed38486b2c334adc5aa44a7968552563d444136566f653479570b", "generation_seconds_batch": 20.7923611960141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.126076340675354, "target_z": -0.12695313536241057, "ce": 6.197352409362793, "genuineness": 4.720732688903809, "identity": 0.5659445524215698, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ab14b25c1f3bbb6d3006827e9b11c6fa51153ffc72406061faff69961cb4ae9b.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "341840ea9aabe33b474492f499c2fe2cdb7380ade83beae2d177b164ca317d8e", "generation_seconds_batch": 16.18498514604289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09668482095003128, "target_z": -0.1826171898150066, "ce": 6.443574905395508, "genuineness": 4.243753433227539, "identity": 0.3503735661506653, "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_Triumph/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "ab96d4a05ca12056e9211b044c0c05010f6cef69695fb6ff1aed23c7e54d3689", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "388ee119054b49bf3b7ffcabe69442237f26df23d69a0bec35c67f778b08bc7a", "generation_seconds_batch": 19.676917723962106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.123668670654297, "target_z": 3.6562499541408213, "ce": 6.340320587158203, "genuineness": 4.105680465698242, "identity": 0.5797600746154785, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ab96d4a05ca12056e9211b044c0c05010f6cef69695fb6ff1aed23c7e54d3689.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "abd69cfccd28b04c00540c8b443743fb370deede50d0df4690b83538bbced9ba", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6c524b76b2a47f27d33dbf207441c9325c50f628bd571bf45cf58f55b08062b6", "generation_seconds_batch": 19.57290887203999, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3381752967834473, "target_z": 4.062500077607841, "ce": 6.022613525390625, "genuineness": 4.168440818786621, "identity": 0.5080463886260986, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/abd69cfccd28b04c00540c8b443743fb370deede50d0df4690b83538bbced9ba.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "ad75cf3c7c04151664465e4cb0361af55260ae8da009bb6df524248053584c4d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "99adb6be2d4e64f2215db065cbcf79ac67e0195addaf796a848402a45338b95d", "generation_seconds_batch": 22.037925477023236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6406858563423157, "target_z": 0.8476562883629667, "ce": 5.831989288330078, "genuineness": 3.9425034523010254, "identity": 0.40907788276672363, "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_Triumph/ad75cf3c7c04151664465e4cb0361af55260ae8da009bb6df524248053584c4d.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": "ad78dd60e76ba52a9b1556956b05cc1ae37e281ea8a5a8cc917c6e13cb6e06fd", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The keys are on the kitchen table.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba8199062aa0e5f98c99f9852b45de1b25acd7b4225375f939f4bdab9ae087c2", "generation_seconds_batch": 21.281649257987738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15108492970466614, "target_z": -0.07958983211984773, "ce": 6.340320587158203, "genuineness": 4.218649387359619, "identity": 0.5172648429870605, "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_Triumph/ad78dd60e76ba52a9b1556956b05cc1ae37e281ea8a5a8cc917c6e13cb6e06fd.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "adb8afb5d6b8d6b67814f12886c38f8616c44123d7c7f929bb443abc1637bb6c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a0dc301d92014eb28bea1aed4d14a42eb643cbbc9c86c5d90e425cd93c6d7bff", "generation_seconds_batch": 14.737742029014044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1666394472122192, "target_z": 1.8437500458591787, "ce": 5.792276382446289, "genuineness": 4.174716949462891, "identity": 0.6629015803337097, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/adb8afb5d6b8d6b67814f12886c38f8616c44123d7c7f929bb443abc1637bb6c.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "d2a91d1bc7d6c2973907ac9da10678204f5c870ebb96ad3ace880e41629b90ab", "generation_seconds_batch": 15.251421405002475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11782609671354294, "target_z": -0.1425781194880795, "ce": 6.173524379730225, "genuineness": 4.300237655639648, "identity": 0.6286114454269409, "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_Triumph/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "adf3d6ead3963aaf0aba32d4d3b90a57742e9343250a325acd2342cea3b0db06", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37fc8597c7442a5ed666b5c288f706c80fb0a806e8f7255cda725092c87ad5ac", "generation_seconds_batch": 21.58282778202556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8926615715026855, "target_z": 3.218749890643497, "ce": 5.669164657592773, "genuineness": 3.8546390533447266, "identity": 0.398029088973999, "hypothesis": "I found the little box! It was beside the old window! We can look inside together!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/adf3d6ead3963aaf0aba32d4d3b90a57742e9343250a325acd2342cea3b0db06.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": "ae1e4bc86d3cf0f91abffba63988b7d8652402e97eb2f5c0b49acf9b750fb6dc", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c47821077b660067bc0f0a3693e7fd5509a313b9815a7ac7f06ae2506b6fb20c", "generation_seconds_batch": 14.720007871976122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2833467721939087, "target_z": 0.1708984199720928, "ce": 6.062326908111572, "genuineness": 4.20609712600708, "identity": 0.745956301689148, "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_Triumph/ae1e4bc86d3cf0f91abffba63988b7d8652402e97eb2f5c0b49acf9b750fb6dc.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "c605b7df0efeb0d6f7ee9f890e746c76a98c3e3ad20bfa3f99d5d8ed31c54e60", "generation_seconds_batch": 16.934162733028643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.045636385679244995, "target_z": -0.2792968752204768, "ce": 6.443574905395508, "genuineness": 4.042920112609863, "identity": 0.3068276047706604, "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_Triumph/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "ae602927989d672047cf8168f5b1fb7d8c8ef376e089a3772e60bca1919b9d08", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4459712694e4387da04e05c386923598331cadedb46445428ac3d9397a9d0c7d", "generation_seconds_batch": 21.48318639001809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6864053010940552, "target_z": 2.8281249629598944, "ce": 6.205295085906982, "genuineness": 4.413206577301025, "identity": 0.06537551432847977, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ae602927989d672047cf8168f5b1fb7d8c8ef376e089a3772e60bca1919b9d08.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "ae7bb8ed9f94abfefaa35f0153b81d9f90c12635528b1692a9185968d77df3a2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fe4de4f4b5007c071809a0cf5b2e1a765abdc6908ea6bdc05666cf63393fc340", "generation_seconds_batch": 19.350619814009406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22018077969551086, "target_z": 0.051269517525317936, "ce": 6.38003396987915, "genuineness": 4.645420074462891, "identity": 0.542605996131897, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ae7bb8ed9f94abfefaa35f0153b81d9f90c12635528b1692a9185968d77df3a2.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "aebdfe88ab3d09b13ba2185f52a4178b8ec1c7e869bbb71791c928595adc155e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9436bf4c87f108d91ada79b46ae8b36f0c85487be03a330c146971575a4f3f6b", "generation_seconds_batch": 22.98101162200328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31789469718933105, "target_z": 0.23632809479467562, "ce": 6.1020402908325195, "genuineness": 4.093128204345703, "identity": 0.6798548698425293, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/aebdfe88ab3d09b13ba2185f52a4178b8ec1c7e869bbb71791c928595adc155e.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "af6f8523944f3fa08c6681352fd12c922cf6c6fbb82fecf50347656bc9a6cc9e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "84c4b608cf622fc057b0038b490b9e1b4ff7fa1a578a50e5dec18c2cb7be0d55", "generation_seconds_batch": 16.88860701303929, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24157987534999847, "target_z": 0.09179686816521856, "ce": 6.252951145172119, "genuineness": 4.20609712600708, "identity": 0.3425135016441345, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/af6f8523944f3fa08c6681352fd12c922cf6c6fbb82fecf50347656bc9a6cc9e.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "af8702409d34ff66d9c28ba42027b52cb4250db2fa9717fbd092ee46c4c4594e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1994ddfddd25b9836f79f56b539e08db614797781abff2d831e2f89cbe75db70", "generation_seconds_batch": 19.874887967016548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16294465959072113, "target_z": -0.0571289095020331, "ce": 6.348263263702393, "genuineness": 4.306513786315918, "identity": 0.4795941114425659, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/af8702409d34ff66d9c28ba42027b52cb4250db2fa9717fbd092ee46c4c4594e.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "b02bd4dea9ee174c36ce9db230a100d7dcf9e9b61ad1e68a9ad5ed83f8169d30", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5d2adb7954f4d1ab73f5e74c1b542b6535491a1b3694024f175fc3dcca57b296", "generation_seconds_batch": 16.47287241392769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17583568394184113, "target_z": -0.032714837411291414, "ce": 6.252951145172119, "genuineness": 4.331617832183838, "identity": 0.43904733657836914, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b02bd4dea9ee174c36ce9db230a100d7dcf9e9b61ad1e68a9ad5ed83f8169d30.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "b033d92181bafa0f017549dd70156e38891475409dd05b81a7d55d25f3fa4c5b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0e2e79c6cce0686cba8b1830b83bae6d6ceb5fc8e52aee0b7592027b61ae4d93", "generation_seconds_batch": 20.464993810048327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2037655115127563, "target_z": 1.9140624109273645, "ce": 6.24500846862793, "genuineness": 4.432034492492676, "identity": 0.40812984108924866, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b033d92181bafa0f017549dd70156e38891475409dd05b81a7d55d25f3fa4c5b.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "b0b2a5930d6e84cdb52f741f2615f3130b787c728ff767d18ac3b5cd6500d0bc", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a20e1293a0bccab3975c1435ba0f90eb61b04fdc8365719b8ffc62639f743b47", "generation_seconds_batch": 19.967199723003432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15314748883247375, "target_z": -0.07568358961605962, "ce": 6.078212261199951, "genuineness": 3.9550557136535645, "identity": 0.6211550235748291, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b0b2a5930d6e84cdb52f741f2615f3130b787c728ff767d18ac3b5cd6500d0bc.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "b124a03f87356e1f7bb25fda9d33e96d387d80a44bd7c30ae2653ff780a511ac", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "765c928f32b53979855b458b28d63f27b2a46638a24f9766bc75e8a50496f33d", "generation_seconds_batch": 19.251474221935496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11473225057125092, "target_z": -0.14843749735427816, "ce": 6.181467056274414, "genuineness": 3.7667744159698486, "identity": 0.3755854368209839, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b124a03f87356e1f7bb25fda9d33e96d387d80a44bd7c30ae2653ff780a511ac.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "b149967e969d665b15381ba171378c007e9134af27a166291e78db2de3089169", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6bc7f38cfdf536d0789a9284bca28aad044815733aa6d0597e29b945814686a2", "generation_seconds_batch": 21.084585590055212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14824889600276947, "target_z": -0.08496094378358938, "ce": 6.0305562019348145, "genuineness": 3.848362922668457, "identity": 0.5023816823959351, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b149967e969d665b15381ba171378c007e9134af27a166291e78db2de3089169.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": "b1c6087ec51519edcefec41609d114e07fe29b73675af67fee3d55174d1f5b08", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "39b953a4b55eb54c818b23fa6cdf5c0a88504c8ffb9e3a2ae9ea2098ef871288", "generation_seconds_batch": 21.04496963310521, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.418960303068161, "target_z": 0.427734372574755, "ce": 6.475345611572266, "genuineness": 4.444586753845215, "identity": 0.7051170468330383, "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_Triumph/b1c6087ec51519edcefec41609d114e07fe29b73675af67fee3d55174d1f5b08.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": "b2193740d5f9fb942cf2fbee720457d3cfe493702f81ba44f52b317dedd288c1", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Your message arrived after I had left.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3150fab29335d8bde243b8d960cede8878b149ed1397d6a00eff5a59ff8ab768", "generation_seconds_batch": 16.12698716891464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24802538752555847, "target_z": 0.10400390421058942, "ce": 6.2767791748046875, "genuineness": 4.036643981933594, "identity": 0.41055387258529663, "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_Triumph/b2193740d5f9fb942cf2fbee720457d3cfe493702f81ba44f52b317dedd288c1.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "b23e2e6e50439dee39a2c5c8e8cd1c45b4d2934ab6cae79a00ae057be18b97f3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "91029eb2146d51bbee56ed3ff1b739c7dc00f67ab1c824affa81dab250b0aff3", "generation_seconds_batch": 21.007641253992915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3398946523666382, "target_z": 2.1718748677139077, "ce": 5.982900142669678, "genuineness": 4.3504462242126465, "identity": 0.4087572395801544, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b23e2e6e50439dee39a2c5c8e8cd1c45b4d2934ab6cae79a00ae057be18b97f3.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "b25408b400ab4cc3b5767eda235f981f1ab2af0ec050602a0d266c0ba2620b83", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "04aff47ff8f26377d5896d3eeaf494d0794f7d37177eaabe06a9aee44d4008f4", "generation_seconds_batch": 19.24701869103592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9851338863372803, "target_z": 1.500000028221033, "ce": 6.0146708488464355, "genuineness": 4.20609712600708, "identity": 0.5301207900047302, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b25408b400ab4cc3b5767eda235f981f1ab2af0ec050602a0d266c0ba2620b83.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "b26c8b91578b3c6fde12b7928e0d4ec9f0627baf6a4c57514d83cd00f42bdd92", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "92e5bc5c45d11beaa6bc83fb32df2275edf02b6576378e9c79349cae74a6d274", "generation_seconds_batch": 19.707173793925904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2114148885011673, "target_z": 0.03466795866318547, "ce": 6.284721851348877, "genuineness": 4.532451152801514, "identity": 0.7032341361045837, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b26c8b91578b3c6fde12b7928e0d4ec9f0627baf6a4c57514d83cd00f42bdd92.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "b2ee7ffa6d3af0c31b3518de0436df334657fa73ac8d4d9550f49b632596b09f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d67496e9ea78d3d7f2ea12b2d169004b4a3e3bbf4c81878cf355a7f4d0f988a6", "generation_seconds_batch": 14.412006384925917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2843780517578125, "target_z": 0.17285154122398683, "ce": 6.070269584655762, "genuineness": 3.860914945602417, "identity": 0.5173972845077515, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b2ee7ffa6d3af0c31b3518de0436df334657fa73ac8d4d9550f49b632596b09f.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "b2f5149d899fcf9fabe6c69f715acabb9f856d12da9e7a5b02217792b4077704", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "79a0f0aadee42991415e48253d86580be8e8358a91415b69fc17345d51d51326", "generation_seconds_batch": 16.18391090503428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22224335372447968, "target_z": 0.055175788250139045, "ce": 6.117925643920898, "genuineness": 4.369274139404297, "identity": 0.6761411428451538, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b2f5149d899fcf9fabe6c69f715acabb9f856d12da9e7a5b02217792b4077704.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "b2f76534ff419cc011246c7a9f6fbdea8330c6b8f5f35d4b0cb2365649f9a046", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c23c9db5c433da670da987425ab1b3b03e735167285576df0be3c80dc273bac5", "generation_seconds_batch": 20.823368347948417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8572549223899841, "target_z": 1.2578124285655101, "ce": 6.292664527893066, "genuineness": 4.281409740447998, "identity": 0.41354870796203613, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b2f76534ff419cc011246c7a9f6fbdea8330c6b8f5f35d4b0cb2365649f9a046.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "b3552553cd1b4ab7fb467b20e7ac988e060d4c4127eb1e697f51d67d18b1b4ad", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f198f2e64067226fed0b180e5f6359e510999d7bf17a9b43573df1f106799df4", "generation_seconds_batch": 15.657435758039355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.655123770236969, "target_z": 0.8749999858894835, "ce": 6.419747352600098, "genuineness": 4.356721878051758, "identity": 0.48422035574913025, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b3552553cd1b4ab7fb467b20e7ac988e060d4c4127eb1e697f51d67d18b1b4ad.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "b368d1ba850fde13966ee445ed9f324380bfc4ed2c72cc3db914bf7822d833b9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b2acedb2a812989ce37635f2ea373537bb9475fc5be14aceab40b5c8011328d", "generation_seconds_batch": 21.642533783917315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20135989785194397, "target_z": 0.015624998236185437, "ce": 5.831989288330078, "genuineness": 3.653805732727051, "identity": 0.2590218484401703, "hypothesis": "The door is still open! I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b368d1ba850fde13966ee445ed9f324380bfc4ed2c72cc3db914bf7822d833b9.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "b3fc6b221b1b0fed4f8ecab05af7907c96e6cc3877685f1132446698e8179714", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0fd058cc7ab91d67aeac6e70d5b6ac3bf43100909c99d45daeffed8fc2479ef7", "generation_seconds_batch": 16.261588896042667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3008785843849182, "target_z": 0.20410159413842371, "ce": 5.863759994506836, "genuineness": 4.149612903594971, "identity": 0.49462026357650757, "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_Triumph/b3fc6b221b1b0fed4f8ecab05af7907c96e6cc3877685f1132446698e8179714.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "6d30b722b3666fcb0441714dc3e2f3c752692765ba48de0bc5894a822d5c9b45", "generation_seconds_batch": 14.975413289037533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.056980475783348083, "target_z": -0.2578125132286092, "ce": 6.24500846862793, "genuineness": 4.432034492492676, "identity": 0.5588595867156982, "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_Triumph/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "b501ea07ba52201f9d1cd3278cdfe0b12e6a945caa0107a4ed92dc04b1aa04ac", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fe4e0f56ed11b869d2b48195ae52f1097c01abacd289086da35e721d94704883", "generation_seconds_batch": 16.261588896042667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2596273124217987, "target_z": 0.12597657473646354, "ce": 5.5817952156066895, "genuineness": 4.042920112609863, "identity": 0.5302896499633789, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b501ea07ba52201f9d1cd3278cdfe0b12e6a945caa0107a4ed92dc04b1aa04ac.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "b57592556bfe6b25378c49c9d811398b6cea45a34fb4e652e4c1abf42ae1e6d9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "533eda8d6def4067a969b6ac102491859337c38e5edf34a2ac30fcbf2df20f52", "generation_seconds_batch": 19.372387353912927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0181349515914917, "target_z": 1.5625001340499067, "ce": 5.692992687225342, "genuineness": 4.093128204345703, "identity": 0.32281115651130676, "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_Triumph/b57592556bfe6b25378c49c9d811398b6cea45a34fb4e652e4c1abf42ae1e6d9.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "b59c8b59831615ec47a24f25e528dd33acdda7f2b30ccbf179263332b9988057", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ff445adc14d9f875922d13923ac5bd232db30fa07f5e418008f2f92e2c8781e4", "generation_seconds_batch": 21.374027344048955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.701186418533325, "target_z": 4.750000112884132, "ce": 5.363371849060059, "genuineness": 3.9173994064331055, "identity": 0.6215678453445435, "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_Triumph/b59c8b59831615ec47a24f25e528dd33acdda7f2b30ccbf179263332b9988057.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "b5ed5ce101f005f53a0065bc500aa771538ae7676a708eaeca6c7b275e634c4f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "64a390ebc82270a8a1873c7cf9dcbcb951b6bba91b0b970833102d8973baf3f3", "generation_seconds_batch": 16.44950224692002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6286535263061523, "target_z": 2.718749947085563, "ce": 5.816103935241699, "genuineness": 4.20609712600708, "identity": 0.34328705072402954, "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_Triumph/b5ed5ce101f005f53a0065bc500aa771538ae7676a708eaeca6c7b275e634c4f.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "b63471a957f85052295d66044a8d3fa9d7f26d9bc08552fb2a2aacaa432b4c16", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "36b3ec971d14c8af19d43ab88119eaa4c920e8db2429b28a677db4ce87d76bcd", "generation_seconds_batch": 19.526320787961595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2061712741851807, "target_z": 3.8125001058288737, "ce": 5.935244083404541, "genuineness": 4.055472373962402, "identity": 0.3569151759147644, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b63471a957f85052295d66044a8d3fa9d7f26d9bc08552fb2a2aacaa432b4c16.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": "b636d06269fe7c1d9a4bb7157dab4a3c25f341baa79c7bb8335234ddbd7408ab", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2ef2b8db5536513028816d10ce240c313dd581b4ea8deb80b33221e01b35286b", "generation_seconds_batch": 14.812916183029301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27664345502853394, "target_z": 0.15820313183478144, "ce": 5.998785495758057, "genuineness": 4.18099308013916, "identity": 0.5875985622406006, "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_Triumph/b636d06269fe7c1d9a4bb7157dab4a3c25f341baa79c7bb8335234ddbd7408ab.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "b66ab8f32fdba18b1cc64ecccf026adba5094a5faf8ec17b2138afe521341df9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fddf2e890a296b164e42ba99717cda9b8762c19a58769b26da0243a9bc79e65c", "generation_seconds_batch": 19.251474221935496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1603664606809616, "target_z": -0.06201171263176824, "ce": 6.324435234069824, "genuineness": 4.099404335021973, "identity": 0.17076332867145538, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b66ab8f32fdba18b1cc64ecccf026adba5094a5faf8ec17b2138afe521341df9.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "b749edb4c9618dc3ea77d6c7bd69e2069b8e38e6cbe1cfe125d49844d88bb782", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "809c34a9d671141a982b6d29be70c5bf78b92aebd220ab927368d59741b1f00d", "generation_seconds_batch": 19.67476446600631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10957583785057068, "target_z": -0.15820313183478144, "ce": 6.316492557525635, "genuineness": 4.582659721374512, "identity": 0.32604753971099854, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b749edb4c9618dc3ea77d6c7bd69e2069b8e38e6cbe1cfe125d49844d88bb782.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "b76adfab834ef65c4ed43f34b18a53edebcb2906b83aeb3851ce6be60d00e528", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "de9bc905df57f80c87a2bedb2bc7febda587541b8510f09aa12d7d3eaca5f0ad", "generation_seconds_batch": 19.306931695900857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3068937063217163, "target_z": 2.109374987653298, "ce": 6.0146708488464355, "genuineness": 3.8671910762786865, "identity": 0.3719996213912964, "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_Triumph/b76adfab834ef65c4ed43f34b18a53edebcb2906b83aeb3851ce6be60d00e528.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "b855f6f7f6e66002896bddbcb762c12e16d1008eb50a2c7d7f6b391371bfc722", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4deb8378e4c5f4732a559abef73d0f1e2ee8637f12df0a4388451e5e10d980b9", "generation_seconds_batch": 19.166989169083536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1662963330745697, "target_z": -0.05078123721234442, "ce": 6.340320587158203, "genuineness": 4.545003414154053, "identity": 0.49372398853302, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b855f6f7f6e66002896bddbcb762c12e16d1008eb50a2c7d7f6b391371bfc722.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "b86efc6f00514ba2d925e3429751a8a22143acc9c3fc3be3532e43be4f99b852", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5a770d208fa424a2b04890472e1fd4430b704e16a6322023aa59d6cdf4b8fb71", "generation_seconds_batch": 20.48541369009763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1583892107009888, "target_z": 1.8281250758440262, "ce": 6.054384231567383, "genuineness": 4.093128204345703, "identity": 0.09054342657327652, "hypothesis": "De deur 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_Triumph/b86efc6f00514ba2d925e3429751a8a22143acc9c3fc3be3532e43be4f99b852.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "b8e6940ce66fcdbed97cb14c99459d5177e09e45e2045211196bbeb0cdd64b5c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "05aea81767e3e1854d8fe1ecfe4a98287eb2dc911f6d3ec672749ab4c6fe3094", "generation_seconds_batch": 19.64174119499512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2843780517578125, "target_z": 0.17285154122398683, "ce": 6.086154937744141, "genuineness": 4.218649387359619, "identity": 0.4064716696739197, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b8e6940ce66fcdbed97cb14c99459d5177e09e45e2045211196bbeb0cdd64b5c.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": "b9829d5d6f246fe9a0547b2efff7b9b140d48b0036d5eed3a1d1c50ab596d5ae", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc3288d194eb28ef747cdb134906c88b899d577ac2fb0bf86d58be19d11803a4", "generation_seconds_batch": 20.497983573935926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08018431812524796, "target_z": -0.2138671862873775, "ce": 6.157639026641846, "genuineness": 4.632867813110352, "identity": 0.7348645925521851, "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_Triumph/b9829d5d6f246fe9a0547b2efff7b9b140d48b0036d5eed3a1d1c50ab596d5ae.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "b9ab4417d994dc2705699d0347312e08cc9e7d51a4cc5afa7df3937c5ca2cbd4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d208d0c54aa44513cf57de9013b06c1f91d3110e885b57bb405813b7406ca94e", "generation_seconds_batch": 21.186136418022215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25086140632629395, "target_z": 0.10937498765329806, "ce": 6.252951145172119, "genuineness": 4.469690799713135, "identity": 0.639137864112854, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/b9ab4417d994dc2705699d0347312e08cc9e7d51a4cc5afa7df3937c5ca2cbd4.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": "ba0ced162d55c7cdb6b31c0f67ab3908f6a0de33ea96601cd417b85842d61318", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21a5902a957b7892157ea2a798894625f27b023eba2367819c8b1caeacd24fe7", "generation_seconds_batch": 16.288600826985203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.140169143676758, "target_z": 3.6874998941711263, "ce": 6.221180438995361, "genuineness": 4.055472373962402, "identity": 0.4338080883026123, "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_Triumph/ba0ced162d55c7cdb6b31c0f67ab3908f6a0de33ea96601cd417b85842d61318.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "ba5838287e143c4eaa78b053d67b2169c03d5c6feae70db6e3d8599fd1ac1107", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cd6a20769771fdc52a5a1809fd2f8c9b86424fd856b9c974c624ac6eac4fa015", "generation_seconds_batch": 16.44950224692002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6699048280715942, "target_z": 2.7968750229295893, "ce": 5.6254801750183105, "genuineness": 3.6663577556610107, "identity": 0.5453148484230042, "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_Triumph/ba5838287e143c4eaa78b053d67b2169c03d5c6feae70db6e3d8599fd1ac1107.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "ba5b09504f6aa0c34a9123f817c8209768831de46940b0f2b20f0e5143502d2a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c9f861ad68f1037588c46edcf60afe6357acc579cc9235ba91a5408de5034417", "generation_seconds_batch": 14.66577497497201, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16436266899108887, "target_z": -0.05444336778067877, "ce": 6.284721851348877, "genuineness": 4.457139015197754, "identity": 0.7536152601242065, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ba5b09504f6aa0c34a9123f817c8209768831de46940b0f2b20f0e5143502d2a.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "ba5cd9cf99caf2215954ed271c9fc2cdc5c4bd26cfcf6734b99650d54f058804", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7375f1079424ab0d8d4406f2354938f594510f092e9f706df9d3d4157b2ddca2", "generation_seconds_batch": 21.94996713194996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08998148888349533, "target_z": -0.19531250617335097, "ce": 6.3641486167907715, "genuineness": 4.030367851257324, "identity": 0.3880857229232788, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ba5cd9cf99caf2215954ed271c9fc2cdc5c4bd26cfcf6734b99650d54f058804.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "ba679fc4e74d37103ee616014722e4897722f5cfcb6658fcc4dd1ae25d36f84d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "23b699c83f91cd3c9ae4b384fcf1ad61c6813204dd87bb2e40d64b08484a1941", "generation_seconds_batch": 23.213921567075886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7359068393707275, "target_z": 2.921875008819073, "ce": 5.2640886306762695, "genuineness": 3.9425034523010254, "identity": 0.6149808764457703, "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_Triumph/ba679fc4e74d37103ee616014722e4897722f5cfcb6658fcc4dd1ae25d36f84d.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "e7f8afd831eb17d4c19a61a916bd315c9a65c6d71b32df51a7e7b5e3b1ccdc15", "generation_seconds_batch": 16.580489767016843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0012912750244140625, "target_z": -0.3632812583781192, "ce": 6.165581703186035, "genuineness": 4.394378662109375, "identity": 0.7460721135139465, "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_Triumph/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "ba7b1e5db7b435f7903c23f5ca013ce297284c25d28585f0770de521400e1d69", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4c2247ae865df22b335eb7f0141c173270fc95e3e7ca37def1546d20e7ba69b6", "generation_seconds_batch": 17.028998297988437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2202661037445068, "target_z": 1.9453125767259334, "ce": 5.526196479797363, "genuineness": 3.9927117824554443, "identity": 0.5461660027503967, "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_Triumph/ba7b1e5db7b435f7903c23f5ca013ce297284c25d28585f0770de521400e1d69.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "bae33c41e16585133a4c143228bbc692463a484bcbbc24d1b8d0a96c7fce04a6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f9743567f5f2e37e52f05903b606abaf256b172c5dcec5fccc89f7917a3a4b98", "generation_seconds_batch": 17.501206881017424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4306474924087524, "target_z": 2.3437499894171125, "ce": 6.133810997009277, "genuineness": 4.243753433227539, "identity": 0.3517131805419922, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/bae33c41e16585133a4c143228bbc692463a484bcbbc24d1b8d0a96c7fce04a6.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "baf669d3c0eecd34c9dbf4e2bae9312bd4add0f0367786ceb63180fe9c0602ac", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "cd4670d849f89ddd8aaca6360264e58ba178e3210c1fad19fca6da7f9308d0cf", "generation_seconds_batch": 20.042222104035318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19710585474967957, "target_z": 0.007568344851089461, "ce": 6.149696350097656, "genuineness": 4.6203155517578125, "identity": 0.5668769478797913, "hypothesis": "J'ai trouvé la 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_Triumph/baf669d3c0eecd34c9dbf4e2bae9312bd4add0f0367786ceb63180fe9c0602ac.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "bc0a09ecb91675f0b69ff8ec673e435aa9e5878d335f9f4699e88b1aa3d84536", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "112c873e38ea83c56a799461bf050ea4755dd5b393c1238c0ba0a4c26636d5d7", "generation_seconds_batch": 19.69986935693305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11421661078929901, "target_z": -0.1494140579802252, "ce": 6.1894097328186035, "genuineness": 4.118232727050781, "identity": 0.6588208675384521, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/bc0a09ecb91675f0b69ff8ec673e435aa9e5878d335f9f4699e88b1aa3d84536.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "bc0ec5f6b3c3cf3c32ea7e918d7f350176fbe0b8d44ecd80f79ae47961146efb", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1ee5295b759355b3276e90b51ea4126cb04a6fc7dedfc93cf36758332ab8f1cf", "generation_seconds_batch": 21.330106509034522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12040429562330246, "target_z": -0.13769531635834437, "ce": 6.24500846862793, "genuineness": 3.9550557136535645, "identity": 0.3532991409301758, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/bc0ec5f6b3c3cf3c32ea7e918d7f350176fbe0b8d44ecd80f79ae47961146efb.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "bc895d7b3c607e13ab2780ebe750988ab8dd51f9972d83cd2a095a6d469fea3d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "654ae9c027ef8a087b09871d6086505948978e7bb22974acd197eaed39630177", "generation_seconds_batch": 20.24716511601582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0989179611206055, "target_z": 3.6093750440953642, "ce": 6.2767791748046875, "genuineness": 4.281409740447998, "identity": 0.2766379714012146, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/bc895d7b3c607e13ab2780ebe750988ab8dd51f9972d83cd2a095a6d469fea3d.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "bd6f48a59c848083cc133529b123505aff38b1631bfac2121a212eb7e598fd3d", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1a2f7c540b2bcf59cdb5cb7af966e97941d669fb162f7782a73b99217ef78436", "generation_seconds_batch": 15.079659659066238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054917916655540466, "target_z": -0.26171875573239733, "ce": 6.062326908111572, "genuineness": 3.9550557136535645, "identity": 0.3221179246902466, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/bd6f48a59c848083cc133529b123505aff38b1631bfac2121a212eb7e598fd3d.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "bdb5a7aa49b8266a8a2a0b52dcd8952fcfa5a33633ba46fdba1e5b6ac9d7698d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3955c05cb04030b8f2a870ad1739bd883ba8533eb66ec02d61aa0fe6c269350e", "generation_seconds_batch": 21.876155265024863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41174131631851196, "target_z": 0.4140624673694306, "ce": 5.9431867599487305, "genuineness": 4.381826400756836, "identity": 0.6002107262611389, "hypothesis": "I found a little box. It was beside the old window. We can look inside together!", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/bdb5a7aa49b8266a8a2a0b52dcd8952fcfa5a33633ba46fdba1e5b6ac9d7698d.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "beb9b2228384cf751dacd9f4ee3fa0b5aab110ef303c4eaa2a0d5da407a65006", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ea0f68fa2c446f27003bf95643cd82b2e0290e4358fc6853e7728d38cc1ed065", "generation_seconds_batch": 21.50377768895123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5526819229125977, "target_z": 4.46875020107486, "ce": 5.788304805755615, "genuineness": 4.111956596374512, "identity": 0.6508647203445435, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/beb9b2228384cf751dacd9f4ee3fa0b5aab110ef303c4eaa2a0d5da407a65006.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "bedf16403302d99d9278166e38c4ea00b9537ab5f47713759a4109d6b031e701", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e3a3c3664b64687d15002478efe775d9e252d5480b294d341fbcc64542a0954c", "generation_seconds_batch": 14.869461063994095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3051743507385254, "target_z": 4.000000197547231, "ce": 5.784333229064941, "genuineness": 4.024092197418213, "identity": 0.5665402412414551, "hypothesis": "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_Triumph/bedf16403302d99d9278166e38c4ea00b9537ab5f47713759a4109d6b031e701.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "befcdb73b5ce2630fdb523cb0153c85026968e5104eb83c7f13d9d60ff8396a4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3d255c766782afcaa8eb84c5de002fd38007a1ecdf9f300f543d56d3bd2fbceb", "generation_seconds_batch": 16.562565749976784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8679108619689941, "target_z": 3.17187498059804, "ce": 6.078212261199951, "genuineness": 4.118232727050781, "identity": 0.4803583025932312, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/befcdb73b5ce2630fdb523cb0153c85026968e5104eb83c7f13d9d60ff8396a4.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "bf7867d564352f1ad1aa092bca8f15454567ab2ec88b47158a574a74451cc4af", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7963938b53fcc3fdef76e8d341dcb34603e89bd6b87a1ef4520df397fb9e3cfa", "generation_seconds_batch": 19.684224909055047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1345844268798828, "target_z": -0.11083982859221861, "ce": 6.221180438995361, "genuineness": 4.281409740447998, "identity": 0.7002711296081543, "hypothesis": "Ik 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_Triumph/bf7867d564352f1ad1aa092bca8f15454567ab2ec88b47158a574a74451cc4af.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "bf8028743f0772fa6b368ac567409fe78fb3397de8f32fdb8fb62430464b24fb", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8dbee5c0cb2419d9a14a1f3ab5db7c5c1e22ecfa203cb9de3ac43c99f120b808", "generation_seconds_batch": 21.20638385694474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8737554550170898, "target_z": 1.2890624814799472, "ce": 5.871703147888184, "genuineness": 3.6412534713745117, "identity": 0.32688868045806885, "hypothesis": "Ik 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_Triumph/bf8028743f0772fa6b368ac567409fe78fb3397de8f32fdb8fb62430464b24fb.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "c0239aa791ef550908e4ad0852deebc35fca2638e2ce79a421861df0debfc0f3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e852b0d098022d463e3a57f6c1c2ea6f0cb9fab150ba8c4478e930afe4e85255", "generation_seconds_batch": 19.448202500934713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1345844268798828, "target_z": -0.11083982859221861, "ce": 6.157639026641846, "genuineness": 4.469690799713135, "identity": 0.7782228589057922, "hypothesis": "Ik heb het klein toosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c0239aa791ef550908e4ad0852deebc35fca2638e2ce79a421861df0debfc0f3.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": "c041652a4de88870a0f8fb220e3854c232e247b106701874aa55e4af0057ee64", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Escribí el número en el sobre.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aacfd2157d62d21283b8230ccdac69d0225e06492e7730bdfbf06f80e11ffeaa", "generation_seconds_batch": 21.262886692071334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0329160690307617, "target_z": 3.4843752839741446, "ce": 6.24500846862793, "genuineness": 4.231201171875, "identity": 0.6456947326660156, "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_Triumph/c041652a4de88870a0f8fb220e3854c232e247b106701874aa55e4af0057ee64.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "c05335bf88a9a0aaad1ccb7a8f852accfc54aacf34303b1e8d8e1b045e30fb18", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "991ad07bba4942ee9f4503cc7653b27dac47c8f2164c898c2e96f4ef5bab03e0", "generation_seconds_batch": 19.08969504397828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035323575139045715, "target_z": -0.2988281159604504, "ce": 6.173524379730225, "genuineness": 4.293961524963379, "identity": 0.6201608777046204, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c05335bf88a9a0aaad1ccb7a8f852accfc54aacf34303b1e8d8e1b045e30fb18.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": "c100306f8457f06cd7931327997294a7f53c9c3816f6ce25e18c7d768a7a8b9a", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba3db86bddeada03fbb363e94452005694bd2714485db7c3c7c29d8fcab789af", "generation_seconds_batch": 20.141228755936027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11524789035320282, "target_z": -0.14746093672833113, "ce": 6.221180438995361, "genuineness": 4.720732688903809, "identity": 0.6996798515319824, "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_Triumph/c100306f8457f06cd7931327997294a7f53c9c3816f6ce25e18c7d768a7a8b9a.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "c1d6827cbc4e9f536e9413b36b402758ea20b355228d7f385e67c13cb88becaf", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "75328eb0c1ca5ed1833eee50c747ca225f6cb075b2a95ab6b09f786c7381a039", "generation_seconds_batch": 14.712841668981127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09823174774646759, "target_z": -0.17968749382664903, "ce": 6.284721851348877, "genuineness": 4.821148872375488, "identity": 0.5200721025466919, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c1d6827cbc4e9f536e9413b36b402758ea20b355228d7f385e67c13cb88becaf.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": "c248dfc0d44ae7daa7ff8349ec98300d971a9689cdca738da3e75a26ac4c42b1", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21c5ecabbb256ad86e43cf0a97cf3c50460a3ef70c5938c38b48e5a5cc5abb1a", "generation_seconds_batch": 20.497983573935926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05182407796382904, "target_z": -0.26757811948807947, "ce": 6.229123115539551, "genuineness": 4.331617832183838, "identity": 0.7076663970947266, "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_Triumph/c248dfc0d44ae7daa7ff8349ec98300d971a9689cdca738da3e75a26ac4c42b1.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": "c29809abf3ea1cfdb0f23c4173adc4891e8c861b718d95a0655320df9bb2f51d", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c8242c8fbbf5a7cdfbde3cf39d213b84dc25c604b68c5a8c96dba7879226d0d6", "generation_seconds_batch": 20.140324271051213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11112276464700699, "target_z": -0.15527343584642384, "ce": 6.213237762451172, "genuineness": 4.055472373962402, "identity": 0.5743372440338135, "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_Triumph/c29809abf3ea1cfdb0f23c4173adc4891e8c861b718d95a0655320df9bb2f51d.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "c2f8a0bd2cd2b4ed66c088ae9d2d00c3cdd3c47eaa33faf87fa7dde07feb6fbd", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c9a58ae9d4014be287a3e9f26ce798045cb1981745c133784ca73009ba1d48f2", "generation_seconds_batch": 20.892394803930074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5746838450431824, "target_z": 0.7226563024734832, "ce": 6.24500846862793, "genuineness": 4.482243061065674, "identity": 0.5809507369995117, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c2f8a0bd2cd2b4ed66c088ae9d2d00c3cdd3c47eaa33faf87fa7dde07feb6fbd.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "6d3cd4792f6164791d17c013f66d8803881037e7e6c229cc24b2194bef9ced76", "generation_seconds_batch": 15.827961358940229, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03738613426685333, "target_z": -0.29492187345666226, "ce": 6.268836498260498, "genuineness": 4.118232727050781, "identity": 0.6162327527999878, "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_Triumph/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "6355d68aa30fe7649ddbb01949354ab972aad5efc791e64a46cc0585fe20bdc3", "generation_seconds_batch": 14.82149106496945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10957583785057068, "target_z": -0.15820313183478144, "ce": 6.23706579208374, "genuineness": 4.394378662109375, "identity": 0.7122699022293091, "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_Triumph/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "c496ac19cdb4c1de5280ab23f5e0e708245cdc84f35a3f87c70dd48ce8d521ee", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e45cfaadfc1f281ad81e8629c55da7a8cbd3f5155dc8edd8a47bd454f7fc32d8", "generation_seconds_batch": 16.701827406068332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2054850310087204, "target_z": 0.023437511464794655, "ce": 6.23706579208374, "genuineness": 3.835810661315918, "identity": 0.5596242547035217, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c496ac19cdb4c1de5280ab23f5e0e708245cdc84f35a3f87c70dd48ce8d521ee.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "c4987c56a36740b5a8575663fb6c4f68f827eb857aeb8f214112224dae9f7f5c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2799c3c0af3bd5b2c1409bc3571430101b7177d79dcaae0b5f2f04e0d48e48cb", "generation_seconds_batch": 22.257823209976777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4199915826320648, "target_z": 0.42968749382664906, "ce": 5.967014789581299, "genuineness": 4.162164688110352, "identity": 0.09056828916072845, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c4987c56a36740b5a8575663fb6c4f68f827eb857aeb8f214112224dae9f7f5c.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": "c49d7a42496c6f4f3cd322b2b778dcdb2a5eec662c138ca75ddc357cb6d6f187", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e121e45546c9a10d9b31d15577c74f57d549348a4ba5585ead3f63b13af0c49c", "generation_seconds_batch": 20.485435885027982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17996080219745636, "target_z": -0.024902352403715196, "ce": 6.213237762451172, "genuineness": 4.356721878051758, "identity": 0.5286125540733337, "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_Triumph/c49d7a42496c6f4f3cd322b2b778dcdb2a5eec662c138ca75ddc357cb6d6f187.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "c4d00ec9cb41a90f396ef831c7bdc49364e6d94fa204a7957b9825033ddd8eee", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4dd6ab8a32f36d97d87cb31248ddd9072adda38ae6f4a9a0f5b0395ec1ee5cb2", "generation_seconds_batch": 19.24701869103592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10235687345266342, "target_z": -0.1718749947085563, "ce": 6.062326908111572, "genuineness": 4.507347106933594, "identity": 0.6785504221916199, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c4d00ec9cb41a90f396ef831c7bdc49364e6d94fa204a7957b9825033ddd8eee.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "c511e9e41950930926bdf66ada967e3725683e5a0a14a52cd307ad832ead2a20", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4c0d323e546c09549d2b75cdb08cf6c5f5ce1d769159ece294c4525ad2cbac65", "generation_seconds_batch": 22.65660486393608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.460209608078003, "target_z": 6.187500063497324, "ce": 6.435632705688477, "genuineness": 4.011539936065674, "identity": 0.48379260301589966, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c511e9e41950930926bdf66ada967e3725683e5a0a14a52cd307ad832ead2a20.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "c57b9b22c46230af82f87a12845f63703b6d3037a71b051e1a15306852a74041", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "72b4bef32ac01baf267d6557d80ff39bd3273b2294f111ea0493f3db1406c79b", "generation_seconds_batch": 22.35543948900886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9174124002456665, "target_z": 3.2656250264572186, "ce": 5.974957466125488, "genuineness": 4.168440818786621, "identity": 0.49983400106430054, "hypothesis": "J'ai trouvé la 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_Triumph/c57b9b22c46230af82f87a12845f63703b6d3037a71b051e1a15306852a74041.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "c615b1dda809a6d72e63a2f38a92684869aac7ff69466404cdf61adf493d7a10", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6288e7ab743acf40c65a9cc5358333ec67c61984e6eb5ed8df7f945dc7f8f7c9", "generation_seconds_batch": 21.13251196302008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.717686891555786, "target_z": 4.781250052914437, "ce": 5.982900142669678, "genuineness": 4.111956596374512, "identity": 0.1395466923713684, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c615b1dda809a6d72e63a2f38a92684869aac7ff69466404cdf61adf493d7a10.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "c689364c51ea67845b060de9f6d3cc5c4ec5b382689033c8e49641c9ef90e8f4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d725d4b01b393aea3309caa3dfd7c95ad3089be349429e89df96e048d8a2e9ae", "generation_seconds_batch": 20.382748274016194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2061712741851807, "target_z": 3.8125001058288737, "ce": 5.748591423034668, "genuineness": 3.9425034523010254, "identity": 0.6009399890899658, "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_Triumph/c689364c51ea67845b060de9f6d3cc5c4ec5b382689033c8e49641c9ef90e8f4.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": "c6b2c14916034a5596b83e130f035146314a1bf220b91d6707acd7e95a09d341", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c7c610139775607aeb2a5e993843eaf2199986c9131f958166d163b751e188b", "generation_seconds_batch": 20.888077132054605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16500721871852875, "target_z": -0.05322266699824499, "ce": 6.117925643920898, "genuineness": 4.293961524963379, "identity": 0.5634456276893616, "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_Triumph/c6b2c14916034a5596b83e130f035146314a1bf220b91d6707acd7e95a09d341.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": "c79f85d08a040aaa15442c52e8968313b96709f95e9c14b33b051e02aeff1464", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "86a42bd72f0d33b1cd2926618789b39c65f450bd8a37255f91288acd3d3997ac", "generation_seconds_batch": 18.485136258066632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2585960328578949, "target_z": 0.12402345348456947, "ce": 6.308549880981445, "genuineness": 4.256305694580078, "identity": 0.3787088394165039, "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_Triumph/c79f85d08a040aaa15442c52e8968313b96709f95e9c14b33b051e02aeff1464.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "c7c608b1f958395cc5bdc7bdfb0543131a76ce8cfebc657c42d68f91d0393322", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "948aa9bcf746b5c59c3453ccb45407fd4ebdcda53adf573637ad4978a46862e4", "generation_seconds_batch": 22.66643609001767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7771581411361694, "target_z": 3.000000084663099, "ce": 5.967014789581299, "genuineness": 4.017816066741943, "identity": 0.5984008312225342, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c7c608b1f958395cc5bdc7bdfb0543131a76ce8cfebc657c42d68f91d0393322.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "916ef69197d0ca9218277c655a63e6d866b6fbe36313763772bae95307ae6394", "generation_seconds_batch": 15.251421405002475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17841388285160065, "target_z": -0.02783203428155628, "ce": 6.308549880981445, "genuineness": 4.444586753845215, "identity": 0.7076587677001953, "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_Triumph/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "c849f42233e01484aafe72d1747d85f5a8366bed7615a7c946277967c503121b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e23e83b2e18ba15358b10e75e07d66b5005a52fc09c16b8e8252ac3158ed7695", "generation_seconds_batch": 21.275733618997037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1171379089355469, "target_z": 1.75, "ce": 6.038498878479004, "genuineness": 4.394378662109375, "identity": 0.34334099292755127, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c849f42233e01484aafe72d1747d85f5a8366bed7615a7c946277967c503121b.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "c87e8afee08d0634184193fc297d29a1c20aa8fe97e77b7f4cce3ff02513a08c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "90e424678b6b6d98750a2137eb59136be816b3431b86580510874b4b37da5784", "generation_seconds_batch": 20.728050720063038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12298250198364258, "target_z": -0.13281249911809273, "ce": 6.117925643920898, "genuineness": 4.243753433227539, "identity": 0.8003652095794678, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c87e8afee08d0634184193fc297d29a1c20aa8fe97e77b7f4cce3ff02513a08c.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "e5cc79fdb89be8ef323c21baa1bdcf71a91918f3903d9e3b4f3bdf341a804007", "generation_seconds_batch": 16.401018964941613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03429229557514191, "target_z": -0.3007812372123444, "ce": 6.324435234069824, "genuineness": 4.306513786315918, "identity": 0.3313426375389099, "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_Triumph/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "c8cbcae4704189969b9d00b9e71e16b2f1f4e7cf160fea6e96d0d4a0494196c5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "62cb2bc29f70f9c42a4fed8fb3888b15bce9036a4baafbcc60829484e1379962", "generation_seconds_batch": 20.45882978697773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1336383819580078, "target_z": 1.7812499400303048, "ce": 5.998785495758057, "genuineness": 3.8797430992126465, "identity": 0.2951369881629944, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c8cbcae4704189969b9d00b9e71e16b2f1f4e7cf160fea6e96d0d4a0494196c5.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "c93fa757c42ce0bcb99e092f05a9e1e1df648f8fd3cf05d0f66471c65cceb68f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b99cb990d813ccb6eb47b86148e49576267ecde6603f7300df75cac068dd6139", "generation_seconds_batch": 16.701827406068332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20857886970043182, "target_z": 0.02929687522047682, "ce": 6.062326908111572, "genuineness": 3.785602569580078, "identity": 0.583712100982666, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c93fa757c42ce0bcb99e092f05a9e1e1df648f8fd3cf05d0f66471c65cceb68f.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "c955ccdf916b79f759f0a39082c3b508bef33927081ec0904e8dc10676f1c356", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a3469f6eb6c78f1bdb27de68b525e8d1f39e9db10e2040784f406832aae2d07b", "generation_seconds_batch": 22.082810263964348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.486679792404175, "target_z": 4.3437499894171125, "ce": 6.0305562019348145, "genuineness": 3.9425034523010254, "identity": -0.054727811366319656, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c955ccdf916b79f759f0a39082c3b508bef33927081ec0904e8dc10676f1c356.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "c9b525d40760e53cf3338629202c1a5e7646dd0d5bc88824cd79de7ba378f731", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "14177bf8660d37e16ead55b5631d300f0e52937dcdc82519a0af2fe28096343e", "generation_seconds_batch": 23.169209641986527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49218130111694336, "target_z": 0.5664062636695628, "ce": 5.974957466125488, "genuineness": 4.168440818786621, "identity": 0.5858608484268188, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c9b525d40760e53cf3338629202c1a5e7646dd0d5bc88824cd79de7ba378f731.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "c9cd3676d6d1945a8339fbcef74a78ec0615b1f693047bb4c4ffc7faf997b4e8", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9b79bbc3090732ad7f7b22306335c628e0876b10c81757e3963ba1a667f9f07a", "generation_seconds_batch": 19.996083856909536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39936596155166626, "target_z": 0.39062501234670194, "ce": 6.173524379730225, "genuineness": 4.419482707977295, "identity": 0.49966609477996826, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/c9cd3676d6d1945a8339fbcef74a78ec0615b1f693047bb4c4ffc7faf997b4e8.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "ca40182ff3e4d42427de84755a4b2c1fcf34d0dabb9299fdab266af3e133f345", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "57bfa2703573239a2b0510975ad9c98fa4e30ee7f6886142fa417b18ae24c45e", "generation_seconds_batch": 20.54424153699074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18975798785686493, "target_z": -0.006347644068655678, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.5863943099975586, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ca40182ff3e4d42427de84755a4b2c1fcf34d0dabb9299fdab266af3e133f345.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "cb17c3f8c0f64c40af1b38a7259b69242bd667872c4096dbc4a17ca8c63265d7", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0bcc08a7c5ac511aa97162ee3894c072290da40c4815094ddf626e730bb3e287", "generation_seconds_batch": 20.412247207015753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18846887350082397, "target_z": -0.008789073854556247, "ce": 5.95112943649292, "genuineness": 3.810706615447998, "identity": 0.31106579303741455, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/cb17c3f8c0f64c40af1b38a7259b69242bd667872c4096dbc4a17ca8c63265d7.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "cb20138d63bb5def32f9fdce4fcd0cd4c7c22a8b4ae11271f58ffbd15c8525c0", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "47feb6092f37bf4913c91d86d8377072be375dec035a7f2e2a8b9c7891534622", "generation_seconds_batch": 22.401101954979822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18950016796588898, "target_z": -0.006835924381629191, "ce": 6.435632705688477, "genuineness": 4.13078498840332, "identity": 0.4855652153491974, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/cb20138d63bb5def32f9fdce4fcd0cd4c7c22a8b4ae11271f58ffbd15c8525c0.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "cb5ec8c7912f4dc127f6a354a073cfaebe1aced51bb4b395d4580cfb6408cf64", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9462095357cbd02c691526ef6c5f3345b059f65e23951c0a9045c10fbceafb4c", "generation_seconds_batch": 20.166203723987564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09565354138612747, "target_z": -0.18457031106690067, "ce": 6.062326908111572, "genuineness": 4.519899368286133, "identity": 0.7704628705978394, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/cb5ec8c7912f4dc127f6a354a073cfaebe1aced51bb4b395d4580cfb6408cf64.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "cb89b15b3e2627cdb10d6fc495d3e8800772bc8b802ff28083e4adda156bee54", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "740cabf2768c5d8c5dc6175b9cee01ac6d87d6edcba0152c33bd055b1aa37a49", "generation_seconds_batch": 15.49826963210944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2611742317676544, "target_z": 0.1289062566143046, "ce": 6.0305562019348145, "genuineness": 4.18099308013916, "identity": 0.7390725612640381, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/cb89b15b3e2627cdb10d6fc495d3e8800772bc8b802ff28083e4adda156bee54.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "cbbdf3ebbf76fe0d7ed0c961a9d0142a1dc3124487371f212b6c5bbe77223f50", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c9be37abe3f6266172a87ddfdfa62f738bde18c619bbc765381ef180fe581de9", "generation_seconds_batch": 21.50529074005317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8184093236923218, "target_z": 3.0781249347388613, "ce": 6.356205940246582, "genuineness": 4.218649387359619, "identity": 0.6173230409622192, "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_Triumph/cbbdf3ebbf76fe0d7ed0c961a9d0142a1dc3124487371f212b6c5bbe77223f50.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "cbe5e2f9d15de7345fc41877928a88e7c229815c8a9c515b8d3dfc81d21ba3ef", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7d112c29ace423c934aeb4ea573d3fe2dc154d88a567c829e7555e5057ade4ce", "generation_seconds_batch": 15.763659035903402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3787403106689453, "target_z": 0.35156247442468885, "ce": 6.213237762451172, "genuineness": 4.457139015197754, "identity": 0.6640592813491821, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/cbe5e2f9d15de7345fc41877928a88e7c229815c8a9c515b8d3dfc81d21ba3ef.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "cc214f80d07d4c0d89118308177e9771c78a73c831a23e1253b17bf3b21151c2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4bc0635d142d38c2e1f8160b9f725ac6658d9c3d70d28412828960866de96c6d", "generation_seconds_batch": 19.310675690998323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20419591665267944, "target_z": 0.020996081678894087, "ce": 6.316492557525635, "genuineness": 4.432034492492676, "identity": 0.49561598896980286, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/cc214f80d07d4c0d89118308177e9771c78a73c831a23e1253b17bf3b21151c2.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "cc99b4fcf61f7301133b9cc7249e4b2e226d69618fc0c15c9a29733c9e6527fe", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ba3c55393757c8db2652c2696faf84a1175245f1909f807d1fab10adb6e08ffd", "generation_seconds_batch": 14.210392058012076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3711764812469482, "target_z": 4.125000409204978, "ce": 6.308549880981445, "genuineness": 4.068024158477783, "identity": 0.4339781403541565, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/cc99b4fcf61f7301133b9cc7249e4b2e226d69618fc0c15c9a29733c9e6527fe.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "cd50ceea05ee9bc3ff6eb12696b244c73b0327177205706fad8e6cd9c264b702", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f34d0c650c4a10f099ad048644c4526dd4757e152070b57f51c0dbfd6528542d", "generation_seconds_batch": 19.904625035007484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5829340815544128, "target_z": 0.7382812724886356, "ce": 6.181467056274414, "genuineness": 4.337893962860107, "identity": 0.3801475167274475, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/cd50ceea05ee9bc3ff6eb12696b244c73b0327177205706fad8e6cd9c264b702.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "cda6c21cd66a0a91e4fd98174d94c8fdb2a2098b26248a9761bf1e8673ff980a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c032e841ed1fb8865eb357947b2ef5a60549190f74c0eb30ec2e218714908cf", "generation_seconds_batch": 19.963971807039343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2622055113315582, "target_z": 0.13085937786619867, "ce": 6.125868320465088, "genuineness": 3.735394239425659, "identity": 0.30298563838005066, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/cda6c21cd66a0a91e4fd98174d94c8fdb2a2098b26248a9761bf1e8673ff980a.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "cda8e383230e6a0bae82cfd78c657f9f75a726c98115ff7893efcfe64a1ce3d9", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fee089c4ada9aef447adb187ce56fc686b38124debb0bbe63906c6cb28fa8e0b", "generation_seconds_batch": 15.667985914973542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5214002132415771, "target_z": 2.5156248853520533, "ce": 5.871703147888184, "genuineness": 4.250029563903809, "identity": 0.28909897804260254, "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_Triumph/cda8e383230e6a0bae82cfd78c657f9f75a726c98115ff7893efcfe64a1ce3d9.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "ce86946ed3c09d052c6ca205e18852a087691c432b9fbebc28016bf14eb8d0fc", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f6188c2b637c9033c1a795a9c990783f3d63fa47c86d9c2ed7960a6a217b3fd2", "generation_seconds_batch": 16.18391090503428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5375576615333557, "target_z": 0.6523437116370333, "ce": 6.252951145172119, "genuineness": 4.068024158477783, "identity": 0.38737553358078003, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ce86946ed3c09d052c6ca205e18852a087691c432b9fbebc28016bf14eb8d0fc.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": "ce8c45c650be5f79266fb5d99f04d6b059a4e7f6ddd588b8d6ce3c001ea14062", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1cf7d714bc79bd616aa46892603061c0d8c39efaf984dd60b1e99fc602ac5010", "generation_seconds_batch": 18.976227204082534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10906019806861877, "target_z": -0.15917969246072847, "ce": 6.300607204437256, "genuineness": 4.444586753845215, "identity": 0.7313532829284668, "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_Triumph/ce8c45c650be5f79266fb5d99f04d6b059a4e7f6ddd588b8d6ce3c001ea14062.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "ceb919d3cda5fba83f1a4262a3b6bb52c48102a3aef15c399617f16cd8a7e436", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7af4e7398ef9d61aa9814a8df3028006aa1867b234a0fb927429fe7b2a4483d", "generation_seconds_batch": 23.306978077976964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3931782841682434, "target_z": 0.3789062848353376, "ce": 5.831989288330078, "genuineness": 3.578493118286133, "identity": 0.39893490076065063, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Hè?", "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_Triumph/ceb919d3cda5fba83f1a4262a3b6bb52c48102a3aef15c399617f16cd8a7e436.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "cf18447bc675318bb64485fd271b391c8f3ac7ba68f6d9f19e80ffbd21d4640e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "351a392cf47a2c2b896163b7920da82a7d35ec80e3237f8a3086011fa0424446", "generation_seconds_batch": 21.274803887004964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13329531252384186, "target_z": -0.11328125837811917, "ce": 6.173524379730225, "genuineness": 3.860914945602417, "identity": 0.6713031530380249, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/cf18447bc675318bb64485fd271b391c8f3ac7ba68f6d9f19e80ffbd21d4640e.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "be76614ceea4600ee2fec8b88c291b1bad21d0c46fa2f1ae0a06e554026e74ca", "generation_seconds_batch": 16.858257316984236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059043049812316895, "target_z": -0.2539062425037881, "ce": 6.4912309646606445, "genuineness": 4.595211505889893, "identity": 0.5920876264572144, "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_Triumph/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "cf827c7c6488d947f8b836ba3b0092f0f1dc30da1001f3aed19dd4b2d2cde941", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "78477866201582be41a1eef6e9d7641f58c4e71ec803cad671010ab9ffe6ac6d", "generation_seconds_batch": 20.4297069250606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2544708847999573, "target_z": 0.11621091203492726, "ce": 6.125868320465088, "genuineness": 4.362998008728027, "identity": 0.4360368847846985, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/cf827c7c6488d947f8b836ba3b0092f0f1dc30da1001f3aed19dd4b2d2cde941.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "d044f3554b84ba0c571be315a517638dc9b075aba0c736060adf0bd2663fca2f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d45fb2804e91316eb0ab2b56f14698540d2c9e826734dc5831889546a9552485", "generation_seconds_batch": 24.763749000034295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4694930911064148, "target_z": 0.5234374832437616, "ce": 6.24500846862793, "genuineness": 4.6705241203308105, "identity": 0.5337109565734863, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d044f3554b84ba0c571be315a517638dc9b075aba0c736060adf0bd2663fca2f.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "d0ab147a81ba47e90257cd7d577745232fe18e740dc19c3f70d0cadabe532073", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6253ed1aacebb876ca1d99106a5cdab5a7f7689f1a460fbc6d8690453912438a", "generation_seconds_batch": 19.40317417110782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17635132372379303, "target_z": -0.03173827678534439, "ce": 6.09409761428833, "genuineness": 4.369274139404297, "identity": 0.5820704102516174, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. C'est A.", "wer": 0.1111111111111111, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d0ab147a81ba47e90257cd7d577745232fe18e740dc19c3f70d0cadabe532073.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "d0dcf8c87bf1d185152ef7d481eb9ebc91a432ddca648079b0062c0d7a6e9210", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "456ac5912d9ba455822868d0014dacb6e2cbf564f384cb6b3707af8a771a37cf", "generation_seconds_batch": 19.4689677299466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.783689022064209, "target_z": 4.906250264572185, "ce": 5.43088436126709, "genuineness": 3.8169827461242676, "identity": 0.5701286792755127, "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_Triumph/d0dcf8c87bf1d185152ef7d481eb9ebc91a432ddca648079b0062c0d7a6e9210.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cd796fca6bf8026e4b84c962887df5db4e119bcd324d64dc5353c1fabed44fd7", "generation_seconds_batch": 16.242263237014413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06729330122470856, "target_z": -0.23828124426760267, "ce": 6.427689552307129, "genuineness": 4.011539936065674, "identity": 0.28676411509513855, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "d152dade67697edeeaa57cb312e4f56c6cbf882f116245fcd3ffb5abe24125c7", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5ae42ed2b42cc8207f43db31997dbee40bde9aff3067b21266ff61cd79393acb", "generation_seconds_batch": 22.380948810954578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3447060585021973, "target_z": 5.968750031748662, "ce": 5.11317777633667, "genuineness": 3.6851859092712402, "identity": 0.5419989228248596, "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_Triumph/d152dade67697edeeaa57cb312e4f56c6cbf882f116245fcd3ffb5abe24125c7.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "d1f254968164d4e2f257a7b36ec4a0b52ad627d561c78205887467d0daeb47ca", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cc13abe31f19d9c0ef1709ca992a35a2606779514870f089eb9e0019e130b32f", "generation_seconds_batch": 14.394905037013814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8349097967147827, "target_z": 3.109374874769166, "ce": 5.7128496170043945, "genuineness": 4.024092197418213, "identity": 0.6354407668113708, "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_Triumph/d1f254968164d4e2f257a7b36ec4a0b52ad627d561c78205887467d0daeb47ca.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "d2162ca002b5a570597d896de78d3785857fab19b5947f309120bb9ef1aebdde", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "28cba041c6c60542a8227225a19c54979ffff122bb7993c15ece7d8e71459f5e", "generation_seconds_batch": 21.05507771705743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11060712486505508, "target_z": -0.15624999647237087, "ce": 6.419747352600098, "genuineness": 4.394378662109375, "identity": 0.5450835824012756, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d2162ca002b5a570597d896de78d3785857fab19b5947f309120bb9ef1aebdde.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "5a8bbba42bac06110ec8e2cfd7ea7d7f7eca6a938fca6892fe6f0143338be9f2", "generation_seconds_batch": 14.775275727035478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06987150013446808, "target_z": -0.23339844113786753, "ce": 6.332377910614014, "genuineness": 4.519899368286133, "identity": 0.724317193031311, "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_Triumph/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "d2979549847d20654c08ba055aa2dfad0a818ea8b23405d914403b011b12d810", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d6c5e31c8df6e24295ec1d11423a1b4402272533dea7311003eb90747176a101", "generation_seconds_batch": 20.48541369009763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26478371024131775, "target_z": 0.1357421809959338, "ce": 6.157639026641846, "genuineness": 3.603597402572632, "identity": 0.49225887656211853, "hypothesis": "De deur 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_Triumph/d2979549847d20654c08ba055aa2dfad0a818ea8b23405d914403b011b12d810.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "d2c6565f8d665ffbe64f2f92879a462b70ebe9d6f8670a1ac95b605178ee329a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9896cc1bf61d321901697295829a72d77b617b0c9551049c809c27d2f1d49242", "generation_seconds_batch": 20.674115338013507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7524073123931885, "target_z": 2.9531249488493776, "ce": 6.372091293334961, "genuineness": 4.143336772918701, "identity": 0.4198759198188782, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d2c6565f8d665ffbe64f2f92879a462b70ebe9d6f8670a1ac95b605178ee329a.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "d355d54dde7c206d3d35fe840d9fa3b135b10e420122841beae01153de198e33", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "87ff0d3eddf649fea96f7273901bb45817093ef1406e37af156c9c1588379ae8", "generation_seconds_batch": 19.390129649895243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07090278714895248, "target_z": -0.231445305775457, "ce": 6.181467056274414, "genuineness": 3.923675537109375, "identity": 0.42174291610717773, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d355d54dde7c206d3d35fe840d9fa3b135b10e420122841beae01153de198e33.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": "d3a1afce1facf5f130d2d42ac4d3d334896a1ea5f4bd25c36ebfbdcbec4991ee", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7857e159affa73538a90a8480f808e779cd8fc1e37f8cfe84ff6702b77b60aa5", "generation_seconds_batch": 15.10113669000566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.767188549041748, "target_z": 4.87500032454188, "ce": 6.1020402908325195, "genuineness": 4.381826400756836, "identity": 0.7060415744781494, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis li bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d3a1afce1facf5f130d2d42ac4d3d334896a1ea5f4bd25c36ebfbdcbec4991ee.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "383f701c4b5725ac043c195c067fc7f61005bd573999b143246ef4561e6fe0af", "generation_seconds_batch": 14.87799242301844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.075886607170105, "target_z": 1.6718749241559738, "ce": 6.205295085906982, "genuineness": 4.570107460021973, "identity": 0.6298813819885254, "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_Triumph/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "d42ef3dbc1b95073cfb7e3a4ac6176cc91f5d040a04b93ef75c5b5824d1409c4", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f9323ef0e600f4795dedafb897a2abd17b6e03e37bb4cb31d874e0abdd7aea17", "generation_seconds_batch": 19.492070795968175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9067564606666565, "target_z": 1.3515624744246888, "ce": 6.427689552307129, "genuineness": 4.218649387359619, "identity": 0.4999125897884369, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d42ef3dbc1b95073cfb7e3a4ac6176cc91f5d040a04b93ef75c5b5824d1409c4.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": "d44ccf6b9a2bf372fda7efeaf7b136de98efe741058e9d2d8a56699894767df6", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The road turns left behind the bridge.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eaa7fa3368d412dbc0310481768bcef7dd35eb5f065a40606a73da6b11f0e4a1", "generation_seconds_batch": 21.597917214035988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08895020931959152, "target_z": -0.19726562742524503, "ce": 6.507116317749023, "genuineness": 4.118232727050781, "identity": 0.3337942957878113, "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_Triumph/d44ccf6b9a2bf372fda7efeaf7b136de98efe741058e9d2d8a56699894767df6.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": "d54b8bfceb94d71ec708fddd557f8b8b0f78528a2c064c23734aa22c192f91ba", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b72bec4d860cbf6f52621b5fb3837fc264b6e6bf97b7e181bd7bbd12fdf3f0fd", "generation_seconds_batch": 19.1614833639469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16939017176628113, "target_z": -0.04492187345666226, "ce": 6.165581703186035, "genuineness": 4.13078498840332, "identity": 0.8171625137329102, "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_Triumph/d54b8bfceb94d71ec708fddd557f8b8b0f78528a2c064c23734aa22c192f91ba.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "d56c1d00bec9ef0d5290ad2f6e9ebfc58b0ebf1f7a00e9ffaa84eb84fcd3a2dd", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3c35f0e3c22dd165e39135ead933c6451107bd4a24f90bc71ea68f204e72a96", "generation_seconds_batch": 14.248142100055702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12839671969413757, "target_z": -0.12255861254564893, "ce": 6.24500846862793, "genuineness": 4.2374773025512695, "identity": 0.5286762714385986, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d56c1d00bec9ef0d5290ad2f6e9ebfc58b0ebf1f7a00e9ffaa84eb84fcd3a2dd.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "d574070445dfb16aa244855c97c0ef2a9388d80a2150d585f3f39988b47ed000", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9f3c2a66373822e5f9e84ea75c3302cc71215f541341c168e6d803a6e455e781", "generation_seconds_batch": 21.239416788099334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.100637435913086, "target_z": 1.7187500599696952, "ce": 5.824047088623047, "genuineness": 3.9425034523010254, "identity": -0.04313087463378906, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d574070445dfb16aa244855c97c0ef2a9388d80a2150d585f3f39988b47ed000.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": "d5d456d54bbc880d7533b0b06a9584a9a04886286bb935d2c5f1795852c4e501", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3021c8ab2ad9b2659890fb379692c8ba58268a79194db856be59ea144210ceba", "generation_seconds_batch": 18.508771699969657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3209885358810425, "target_z": 0.24218745855035778, "ce": 6.197352409362793, "genuineness": 4.3504462242126465, "identity": 0.6372919678688049, "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_Triumph/d5d456d54bbc880d7533b0b06a9584a9a04886286bb935d2c5f1795852c4e501.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "d5e992a7b1ac8ebed3a293ab4f9b35fedcb6a4800f73ff795a1947756eebf554", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d2c769ac9e62c616ce298346ea145f732f20784940301bb60d982a478cb60eed", "generation_seconds_batch": 22.28774522000458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2226717472076416, "target_z": 3.8437500458591787, "ce": 6.268836498260498, "genuineness": 4.093128204345703, "identity": 0.21665146946907043, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d5e992a7b1ac8ebed3a293ab4f9b35fedcb6a4800f73ff795a1947756eebf554.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": "d76f1e2324d52dbe93b3e52c51beefd47cd13ce8bc12871b1018da8b12526494", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "971029bfadaf189fc5a8ee03247bfab4085a4b2587dec2952b68a588a70b74f0", "generation_seconds_batch": 19.707058983971365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11782609671354294, "target_z": -0.1425781194880795, "ce": 6.260893821716309, "genuineness": 4.557555198669434, "identity": 0.6243547201156616, "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_Triumph/d76f1e2324d52dbe93b3e52c51beefd47cd13ce8bc12871b1018da8b12526494.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "d7b314f522f64d44167054916e18b669d6a3606d8b2c7d5606f2dd51adcb922d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "357ff4dc017ce4a75207d6f5a7dfcbda0be229a199c5d311d646700fecafb01c", "generation_seconds_batch": 21.674069302040152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14928017556667328, "target_z": -0.08300782253169532, "ce": 6.117925643920898, "genuineness": 4.519899368286133, "identity": 0.605239748954773, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d7b314f522f64d44167054916e18b669d6a3606d8b2c7d5606f2dd51adcb922d.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "d7cef99e9afe26157d6aca65b85298c71957b0845063ebb1544e2e51feaec223", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "daca0ac2b7dc40eda07d04f3ed56518ef0ca64bedf174f5bfa74efd44a5416ca", "generation_seconds_batch": 16.57467593997717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6736868619918823, "target_z": 0.9101562813077085, "ce": 6.165581703186035, "genuineness": 4.319066047668457, "identity": 0.49725183844566345, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d7cef99e9afe26157d6aca65b85298c71957b0845063ebb1544e2e51feaec223.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": "d7d0b55cc5becac0ec189a036c8420bba27c6fc0682e0bd4210bcc2130203730", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b96633288f2ed0aa05584809b0c537d56ab83d972e4b05ce9ea275953d5c8336", "generation_seconds_batch": 14.878308417042717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20961014926433563, "target_z": 0.031249996472370874, "ce": 5.871703147888184, "genuineness": 4.068024158477783, "identity": 0.0018082298338413239, "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_Triumph/d7d0b55cc5becac0ec189a036c8420bba27c6fc0682e0bd4210bcc2130203730.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "d7ff2002692dfe24555e8046b6a07d9fc9d8d20c5c10618c58ff47369f2216b5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7cc7817d683630eec850365f82fbfccc288e72931652a8eddb729e3cf19e049a", "generation_seconds_batch": 24.763749000034295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6699048280715942, "target_z": 2.7968750229295893, "ce": 6.109982967376709, "genuineness": 4.381826400756836, "identity": 0.6065779328346252, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d7ff2002692dfe24555e8046b6a07d9fc9d8d20c5c10618c58ff47369f2216b5.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "d88bb085e7af129e01e9806fee5b30958139efdfe8f02c8dda78be3e0e9cc108", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a08a6bd508704f07452f3a011f43b42cd74b9f856af71c0d2a96bdc97b423abb", "generation_seconds_batch": 14.470958753023297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.816003680229187, "target_z": 1.179687465605616, "ce": 6.09409761428833, "genuineness": 4.243753433227539, "identity": 0.18027672171592712, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d88bb085e7af129e01e9806fee5b30958139efdfe8f02c8dda78be3e0e9cc108.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "d89f45cc390acb210d3d65717728489ee4e482a27a1acd30470ed88ec9464f47", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3b2a98801964eaae95b85b0e4726e68a33228895d84583c5056b7af1b51187b8", "generation_seconds_batch": 22.401101954979822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2034224569797516, "target_z": 0.019531240739973546, "ce": 6.38797664642334, "genuineness": 4.595211505889893, "identity": 0.5963940620422363, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/d89f45cc390acb210d3d65717728489ee4e482a27a1acd30470ed88ec9464f47.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "da4ebdba1c3a8727430736caa81c16249a9e505588a951ba8c40e605bfab6929", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ecec02791a0b7bedb998dc432d61eef663a60a193594a3ba5021867cad9ed894", "generation_seconds_batch": 21.342429836979136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3711764812469482, "target_z": 4.125000409204978, "ce": 5.661221981048584, "genuineness": 3.9048471450805664, "identity": 0.4346226155757904, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¡Podemos mirar juntos lo que hay dentro!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/da4ebdba1c3a8727430736caa81c16249a9e505588a951ba8c40e605bfab6929.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "da79c42b40f1fe7fbd97f669cf2a7779edca9998ead7a874722fa9847201dd1e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2454d2de6e7b8b91e37603929365ca18935d442188c092fc06023e63365c5454", "generation_seconds_batch": 19.333409009967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6571863293647766, "target_z": 0.8789062283932716, "ce": 6.022613525390625, "genuineness": 3.8797430992126465, "identity": 0.5601320266723633, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/da79c42b40f1fe7fbd97f669cf2a7779edca9998ead7a874722fa9847201dd1e.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "db039746bc9ed64afc19f104a8d6aee5cd3db7df23dfe7e768e5e1b9fb1faee5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d61115e24549a4052e053e3a30e0cdbb7519ff22b68ed00df7c17991323f3df8", "generation_seconds_batch": 19.526320787961595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9916646480560303, "target_z": 3.4062499823618544, "ce": 5.919358730316162, "genuineness": 4.030367851257324, "identity": 0.3371818959712982, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/db039746bc9ed64afc19f104a8d6aee5cd3db7df23dfe7e768e5e1b9fb1faee5.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "12f23313afe52e99a0623cba9099f2f158f79170c132a8d1b376c713787b0a88", "generation_seconds_batch": 16.18498514604289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06419944763183594, "target_z": -0.24414063624431784, "ce": 6.38797664642334, "genuineness": 4.118232727050781, "identity": 0.28405165672302246, "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_Triumph/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "db264ef3553c39d34e6f82043fcf3d315222341b235fc0e64a5c2d9d4b2194e7", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cd761239458e788a1fc728f1d212a99cf81a52569e8e31e21a257a4cfa31b00d", "generation_seconds_batch": 21.51909775810782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.047697067260742, "target_z": 5.4062502081301185, "ce": 5.232317924499512, "genuineness": 3.8420867919921875, "identity": 0.5028516054153442, "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_Triumph/db264ef3553c39d34e6f82043fcf3d315222341b235fc0e64a5c2d9d4b2194e7.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "dc9e61aa0f48974d32b8c9f8ceaa29220009839cee4b745dc8c22a159b18db08", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "faf6fc9258b2922d50ba8b560b9b816f888166a85a4d5aa8c0fee31144231b5a", "generation_seconds_batch": 20.876751233940013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7108129858970642, "target_z": 0.9804687592600264, "ce": 5.9431867599487305, "genuineness": 3.7291181087493896, "identity": 0.6018573045730591, "hypothesis": "De deur 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_Triumph/dc9e61aa0f48974d32b8c9f8ceaa29220009839cee4b745dc8c22a159b18db08.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "dcba58de0604c10e4c8f0ade3445f823714448a27085bfa1be382f2d4ff95289", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "da07d8907eca1db8fc9c0abae682e712291db5b6f44765146d717e173bbdce3b", "generation_seconds_batch": 14.66577497497201, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2972690761089325, "target_z": 0.19726561331472853, "ce": 6.284721851348877, "genuineness": 4.494794845581055, "identity": 0.607480525970459, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/dcba58de0604c10e4c8f0ade3445f823714448a27085bfa1be382f2d4ff95289.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "dd01764da6cde230082a4595a7fb96fc18fbcc7cc270b09b305ff10c503ea547", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bbfa65d06d1e3eec41477c34d8d9162d113ba8badebd0ecf67ec6b688eb495d7", "generation_seconds_batch": 19.311582899070345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15211620926856995, "target_z": -0.07763671086795368, "ce": 6.1020402908325195, "genuineness": 4.174716949462891, "identity": 0.6131634712219238, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/dd01764da6cde230082a4595a7fb96fc18fbcc7cc270b09b305ff10c503ea547.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "dd135308494cf7c7a733e0973327f61d3050c7707850c6f3133ad5f9fd9a2d9b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "aa1b0e584b39275ac8716368ea6113e9b538bbff2721f21f8302e2a0833875a9", "generation_seconds_batch": 19.676917723962106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.80018949508667, "target_z": 4.93750020460249, "ce": 6.435632705688477, "genuineness": 4.369274139404297, "identity": 0.6365501880645752, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/dd135308494cf7c7a733e0973327f61d3050c7707850c6f3133ad5f9fd9a2d9b.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": "dd4f0085a52e40402f867830c172551ed5a4e1f110d603cb5848c48b456b3cdc", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4a1ca802addf244b1576c70a0dc710715bc50506e51e6add21825e6c468e49c", "generation_seconds_batch": 17.31276587001048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1271076202392578, "target_z": -0.1250000141105165, "ce": 6.24500846862793, "genuineness": 4.15588903427124, "identity": 0.6967172622680664, "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_Triumph/dd4f0085a52e40402f867830c172551ed5a4e1f110d603cb5848c48b456b3cdc.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "dda27dac35ee6412014740f0d83e3a5fdbaa83e14409299e50ed13d2c25d6816", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "276bc0347603434a162577cd6807a2298c0dff3b3653d78374afd9deb9502db6", "generation_seconds_batch": 21.578249484999105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3711764812469482, "target_z": 4.125000409204978, "ce": 6.038498878479004, "genuineness": 4.174716949462891, "identity": 0.3834207355976105, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/dda27dac35ee6412014740f0d83e3a5fdbaa83e14409299e50ed13d2c25d6816.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "dde18fe2d7796d93a20a848adf46251d63254bf228457affed1790de5bb02862", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "430f1a37dbf282454f20eb0cf0366c768604cfdf18dcf4776d306aa448a07307", "generation_seconds_batch": 23.341752488981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25240832567214966, "target_z": 0.11230466953113914, "ce": 5.792276382446289, "genuineness": 3.6789097785949707, "identity": 0.4476555585861206, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/dde18fe2d7796d93a20a848adf46251d63254bf228457affed1790de5bb02862.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": "de2c07ee0b2c8ecdb5fbaa08ccf202ac7364617da607882db6f1ebb5ba5b421d", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eeffe98f957ea1c8b826b30b3569440441127b60eccbd3000afebce229341633", "generation_seconds_batch": 19.707058983971365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02810460329055786, "target_z": -0.31249999294474173, "ce": 6.268836498260498, "genuineness": 4.469690799713135, "identity": 0.7837966680526733, "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_Triumph/de2c07ee0b2c8ecdb5fbaa08ccf202ac7364617da607882db6f1ebb5ba5b421d.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "dea592328f0c0984c316c1bc63a3dbc4437527b700e10f133b0e5de8b9874749", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ee10c1096eb41bc6a12e13121dc2f765255989811c73f3ca404231911ec685aa", "generation_seconds_batch": 21.084585590055212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9438825845718384, "target_z": 1.421874952377007, "ce": 5.967014789581299, "genuineness": 3.672633647918701, "identity": 0.596764326095581, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/dea592328f0c0984c316c1bc63a3dbc4437527b700e10f133b0e5de8b9874749.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "dec5de6d2e375f58b158c04eda9488b53177f649c7c7e809691b00ca6f529204", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fa9615be45a32d6a21bb771b34c5e93cef67d8d304a2285d54a7c693a42819c0", "generation_seconds_batch": 19.62406453001313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24003295600414276, "target_z": 0.08886718628737748, "ce": 6.1894097328186035, "genuineness": 4.099404335021973, "identity": 0.6352123022079468, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/dec5de6d2e375f58b158c04eda9488b53177f649c7c7e809691b00ca6f529204.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "def8a2501384cb50649e1e518aed1939da8af08aa6764c0b08997dc1f03e1898", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "026408367170dfb36260ba8cb0549eb3d09ba63910b97dff2d3efb2f67ad8e37", "generation_seconds_batch": 14.88913283299189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6616545915603638, "target_z": 2.781250052914437, "ce": 5.847874641418457, "genuineness": 4.394378662109375, "identity": 0.627036988735199, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/def8a2501384cb50649e1e518aed1939da8af08aa6764c0b08997dc1f03e1898.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "df18def265b227fb2673e374761aa57aa2a5409f61c01ab32556fc0819d76430", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5752bece14506448470c0f3f495343c678c793f12114b6dfd6b51a80487e0bf8", "generation_seconds_batch": 21.65494827996008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.338520348072052, "target_z": 0.27539063271668873, "ce": 5.764476776123047, "genuineness": 3.898571252822876, "identity": 0.4018876552581787, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/df18def265b227fb2673e374761aa57aa2a5409f61c01ab32556fc0819d76430.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "df24826b6247f1c1154dbffda046090d7f73ddcfaeec2101c14e1aacbf3d61ca", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "40886055f357a75fdceaa2d3c42a42d3eadfdecbf58af8353e4b2b323e0794bd", "generation_seconds_batch": 21.90100623096805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0552610158920288, "target_z": 1.6328124991180928, "ce": 6.38003396987915, "genuineness": 4.20609712600708, "identity": 0.2775381803512573, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/df24826b6247f1c1154dbffda046090d7f73ddcfaeec2101c14e1aacbf3d61ca.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "df3e3d2687121c40f7f887cc2985dfa28fa1522bc3f2a4aa32cf05c0c472196f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0d0b8e3cb8a5f23e1cbdaef52eb888caa6fbee31d02f4f300fb1f75f04c45e85", "generation_seconds_batch": 21.587612701929174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7953780293464661, "target_z": 1.140624927683603, "ce": 6.09409761428833, "genuineness": 3.7793264389038086, "identity": 0.5755866169929504, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/df3e3d2687121c40f7f887cc2985dfa28fa1522bc3f2a4aa32cf05c0c472196f.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": "df3f1722f6655db3bdd8fb04d4d193786247eb5edddb2ba6482ba76a82e3003f", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3cdbdd2e98b9cf59e13340187c2deec599899a150d0f2372f2a9b3b84f8ccdaa", "generation_seconds_batch": 21.04496963310521, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5849966406822205, "target_z": 0.7421875149924237, "ce": 6.372091293334961, "genuineness": 4.582659721374512, "identity": 0.437056303024292, "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_Triumph/df3f1722f6655db3bdd8fb04d4d193786247eb5edddb2ba6482ba76a82e3003f.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "df50100f038cd2104372cb3fc2fbbd3b700caede8fbd5fb6350da128d4f363ce", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d349a5f1ac1b4bc85bfbd25315632d520e732a08e55adc2966581c30baff0ca4", "generation_seconds_batch": 19.2749380110763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0729653462767601, "target_z": -0.22753906327166887, "ce": 6.062326908111572, "genuineness": 4.6705241203308105, "identity": 0.7011460065841675, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/df50100f038cd2104372cb3fc2fbbd3b700caede8fbd5fb6350da128d4f363ce.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "df585b406b6eeb813c487c76fb854bbe3be9af45279be6d96f56823280908508", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "963ad0a1b971ece3ac376f535ddcab8ee7e808aa8a47f0532bade3c4026dcf1e", "generation_seconds_batch": 22.68229919602163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38183414936065674, "target_z": 0.357421838180371, "ce": 6.308549880981445, "genuineness": 4.15588903427124, "identity": 0.4884449541568756, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/df585b406b6eeb813c487c76fb854bbe3be9af45279be6d96f56823280908508.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "df5ed5ee6d50d5d0a6e679f066c409d7b1296b6edc535dc51814a29e6c58a586", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "01259352bc0e189b0cd348c57061637356d7ef8d1557b733f2631ea6b5bd31fc", "generation_seconds_batch": 21.664035146008246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.282142996788025, "target_z": 2.0625000776078406, "ce": 5.77639102935791, "genuineness": 4.344170093536377, "identity": 0.48442912101745605, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/df5ed5ee6d50d5d0a6e679f066c409d7b1296b6edc535dc51814a29e6c58a586.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "dfabce4909627ab70e47d86556c462875597265c5237150def9d6ac5eb3cbf83", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e94a5d060e7e6f453209b9d637b077c87f9388b2693d5391011be63da662f453", "generation_seconds_batch": 16.32297155004926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.138967365026474, "target_z": -0.10253906327166887, "ce": 6.284721851348877, "genuineness": 3.9801597595214844, "identity": 0.1313508301973343, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/dfabce4909627ab70e47d86556c462875597265c5237150def9d6ac5eb3cbf83.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "dff66daa1eb6560af6d9611417067a99221a917828698e749d6197bf8a18c10f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "47c3d50ada67e45ff5b850e1d2aaf12055cc5d62f58e261aec32b6fa917a3e88", "generation_seconds_batch": 19.263623476028442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0146961212158203, "target_z": 5.3437503280695084, "ce": 6.348263263702393, "genuineness": 3.8169827461242676, "identity": 0.30591142177581787, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/dff66daa1eb6560af6d9611417067a99221a917828698e749d6197bf8a18c10f.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "e06d1dd09aad65f9fc98b6efcd645e7f3750566ff81ea8230203355305cd1fa6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0466521d39cf5a9cc8a00c282a5d1795955e0212ce5849deef98bcf791b62529", "generation_seconds_batch": 21.275733618997037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.230921983718872, "target_z": 3.859375015874331, "ce": 6.038498878479004, "genuineness": 3.848362922668457, "identity": 0.19263586401939392, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e06d1dd09aad65f9fc98b6efcd645e7f3750566ff81ea8230203355305cd1fa6.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "e079d9c9335939c049dbd000c1e3301cf198f07a616a5321c9f21b6e5707472a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1de6d841dfb346e97151dd8c7fa1370e5a0265b2c2afc4092632bcebb45229e6", "generation_seconds_batch": 21.578249484999105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27973729372024536, "target_z": 0.1640624955904636, "ce": 6.117925643920898, "genuineness": 4.250029563903809, "identity": 0.5752103328704834, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e079d9c9335939c049dbd000c1e3301cf198f07a616a5321c9f21b6e5707472a.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "e0f395ad8f907bc665cf5a958e247e99ce17099a97740bcf34b6313e22840937", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f473074ca40c4098ed2d9eed6c292af084d81c8e28aedefb5810259f77492fae", "generation_seconds_batch": 19.347679002094083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0305103063583374, "target_z": 1.5859375890726355, "ce": 6.292664527893066, "genuineness": 4.557555198669434, "identity": 0.722923755645752, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e0f395ad8f907bc665cf5a958e247e99ce17099a97740bcf34b6313e22840937.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "e137982b2f0aefaeb4646f0981b9423950dc33695f83979d43102873aee9af43", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "161c117bad109314296090bf08ff02bab25921179aad235ef36d50e605683681", "generation_seconds_batch": 14.893929666024633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1652650386095047, "target_z": -0.05273438668527148, "ce": 6.229123115539551, "genuineness": 4.105680465698242, "identity": 0.5495560765266418, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e137982b2f0aefaeb4646f0981b9423950dc33695f83979d43102873aee9af43.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "e16a34de10a8dc8f61efd22b3c38d1142e19d5701ed1fab164ec33ca2e90df2b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b444bfca53e3a78126cc8022829d3fa657ddc54b6450d8aa7d655f3b588cd43d", "generation_seconds_batch": 22.079803666914813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074167251586914, "target_z": 3.5625001340499067, "ce": 5.895530700683594, "genuineness": 4.2249250411987305, "identity": 0.6472064256668091, "hypothesis": "J'ai trouvé la 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_Triumph/e16a34de10a8dc8f61efd22b3c38d1142e19d5701ed1fab164ec33ca2e90df2b.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "e177954f02a21a8de9bcff5d35d062d9cf79820147c540ec7cd123c2ff57ea07", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e4d3feaf1e4bdde7dea047f7b30de494ee228708b707f6a8a0917c911618ca68", "generation_seconds_batch": 21.58282778202556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3893961906433105, "target_z": 2.2656249135730864, "ce": 5.863759994506836, "genuineness": 4.287685871124268, "identity": 0.6287076473236084, "hypothesis": "I found the little box It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e177954f02a21a8de9bcff5d35d062d9cf79820147c540ec7cd123c2ff57ea07.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": "e1ab059bc679896af0f975dccdf01bfd6bf4e5fe57a98766cf33049e57e0ed6d", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Someone moved the little blue chair.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eca931b402c1e630e597fcf58f39d72593f587d256f218a01bdd50718e493b30", "generation_seconds_batch": 21.059687986038625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08791892975568771, "target_z": -0.19921874867713907, "ce": 6.332377910614014, "genuineness": 4.344170093536377, "identity": 0.40606531500816345, "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_Triumph/e1ab059bc679896af0f975dccdf01bfd6bf4e5fe57a98766cf33049e57e0ed6d.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": "e1b734e23671385b438de041252f7558074396689d47bd96c17907d084e50679", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Your message arrived after I had left.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "88b6e4489b6e85f97086e43b08550f5b5fabfa249770c4ecd08a0a170ae957c9", "generation_seconds_batch": 16.12698716891464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3684275150299072, "target_z": 0.3320312619057483, "ce": 6.197352409362793, "genuineness": 3.8797430992126465, "identity": 0.4866628646850586, "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_Triumph/e1b734e23671385b438de041252f7558074396689d47bd96c17907d084e50679.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": "e23212a25affdfdf6644b3952a2abef2e2b63645dee78004e254cfd9bd26b03d", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04f2fd533a4a1e591ac40eac3389cbc161f14b42539b85e9489ab3cb55ae0aa6", "generation_seconds_batch": 15.133425218984485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44886744022369385, "target_z": 0.4843749453217486, "ce": 5.935244083404541, "genuineness": 3.8044304847717285, "identity": 0.6338152289390564, "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_Triumph/e23212a25affdfdf6644b3952a2abef2e2b63645dee78004e254cfd9bd26b03d.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "e234463d827da651fea348be993a5a64c306dfccaa940edb75c348e54a491346", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6a473abc57444043bb19b84704fb8528da2ceda5426a12ae20d089362b06127c", "generation_seconds_batch": 16.320018262020312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23565000295639038, "target_z": 0.08056639274579476, "ce": 6.09409761428833, "genuineness": 3.8671910762786865, "identity": 0.32478654384613037, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e234463d827da651fea348be993a5a64c306dfccaa940edb75c348e54a491346.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "e23fecc5f3882fbb52e54f3cb4ea61fe12024111e8f49198d63c940ff61a43cc", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "095729484e7911ce99aad741c4b296e4730b17b9a1f760e8c72a125fa7608963", "generation_seconds_batch": 19.30284366104752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.132521852850914, "target_z": -0.11474609931703972, "ce": 6.197352409362793, "genuineness": 4.68307638168335, "identity": 0.5549503564834595, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e23fecc5f3882fbb52e54f3cb4ea61fe12024111e8f49198d63c940ff61a43cc.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": "e2444aaa08e9293c11593192134afe988a038227b3b4dff5e2858164aa8a9a90", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ff8838a95aa2d64a6c3dbe1f1ee70118c70439a6eb178c76a59366b07c2ffe1", "generation_seconds_batch": 15.162730304989964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2570490837097168, "target_z": 0.12109371516466239, "ce": 6.141753673553467, "genuineness": 4.086852550506592, "identity": 0.2268349528312683, "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_Triumph/e2444aaa08e9293c11593192134afe988a038227b3b4dff5e2858164aa8a9a90.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "e271b2297b5e1ea24a12135077b94f830208e5bb60ffc3fbe3146f8ce0e9cc4c", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a9f787bac70e41d3a2dd5243d3401ac63a8c50048b184fb419863f04c9e4a9d2", "generation_seconds_batch": 16.375231671030633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1732574701309204, "target_z": -0.037597668762059555, "ce": 6.332377910614014, "genuineness": 4.557555198669434, "identity": 0.811704158782959, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e271b2297b5e1ea24a12135077b94f830208e5bb60ffc3fbe3146f8ce0e9cc4c.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "e3ae2e0b5c25da033c7e187d3f8f6b5a40187420f75dcde7bb0bdb46f66fafa2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "741eed45bd6e1c3668ed6e8c1b6421013a0fb26d1f9667df2109e65073a4e138", "generation_seconds_batch": 21.65494827996008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4550551772117615, "target_z": 0.4960937857172449, "ce": 5.589737892150879, "genuineness": 3.6914620399475098, "identity": 0.08776132017374039, "hypothesis": "Ik 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_Triumph/e3ae2e0b5c25da033c7e187d3f8f6b5a40187420f75dcde7bb0bdb46f66fafa2.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "e44324460a6f0714b17583c532b9a3874ee5b42f3920e8a4d0f5ba94d55cdbfe", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c807d134fe672871113dd4c3e5ae7435d4c6132f2c8590384c0ecae01b4b1e00", "generation_seconds_batch": 19.81654214602895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20135989785194397, "target_z": 0.015624998236185437, "ce": 6.213237762451172, "genuineness": 3.8169827461242676, "identity": 0.5828946232795715, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e44324460a6f0714b17583c532b9a3874ee5b42f3920e8a4d0f5ba94d55cdbfe.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "e53be8108d307f004cd5421557925dc9b4b47d21c1f1ab44b14a5d029aa7e2cf", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2a8cd3906d6eae796571b953b7289994108d0c1a5a47ac598dd9b9c8f6085c02", "generation_seconds_batch": 21.49624779797159, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8596606254577637, "target_z": 3.1562500105828875, "ce": 6.252951145172119, "genuineness": 3.936227321624756, "identity": 0.1986314058303833, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e53be8108d307f004cd5421557925dc9b4b47d21c1f1ab44b14a5d029aa7e2cf.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "e5724c7942bc60fbf27b472bab6c23841fa6eee8bcbdf8b6242c2993a3b5be16", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ea7546b121cf80e7ab37c9f52b9684831b0efe35100d2284fa9db18062bfd20b", "generation_seconds_batch": 20.587496717926115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.008165121078491, "target_z": 3.4374999223921594, "ce": 6.443574905395508, "genuineness": 4.331617832183838, "identity": 0.4461231827735901, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e5724c7942bc60fbf27b472bab6c23841fa6eee8bcbdf8b6242c2993a3b5be16.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": "e5a7ec02d4c0194e63c1b63f0df4d3c725a6de2cb1d104a984b48bdf45e5e2e0", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I wrote the number on the envelope.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9bccbe278bd47cc8eb114881421e48ae2ddbd565ed1a52bae3932a50619af73", "generation_seconds_batch": 16.691096780006774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.086372010409832, "target_z": -0.20214843055498016, "ce": 6.332377910614014, "genuineness": 4.256305694580078, "identity": 0.33228379487991333, "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_Triumph/e5a7ec02d4c0194e63c1b63f0df4d3c725a6de2cb1d104a984b48bdf45e5e2e0.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": "e5d6cb6da46460a25e6b4a7614f9758af326b7fe4edaf37cfbb7a6d34dab7389", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I wrote the number on the envelope.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1d6247cbcc474512e43e71191db4867868e98cfc5353841650aa82b423057bec", "generation_seconds_batch": 20.47239745594561, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.059386134147644, "target_z": 1.640624984125669, "ce": 6.395919322967529, "genuineness": 3.9425034523010254, "identity": 0.24388718605041504, "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_Triumph/e5d6cb6da46460a25e6b4a7614f9758af326b7fe4edaf37cfbb7a6d34dab7389.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "e5ed05becbc45bb7ac192212313b41cf47be7821a42c32520f2a9bc388947270", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3f59bca7d77f3e66ec7b6190fc389df46b5b3232510defb54b59db38dfdc00c8", "generation_seconds_batch": 19.548025041935034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42308545112609863, "target_z": 0.4355469140243972, "ce": 5.982900142669678, "genuineness": 4.061748504638672, "identity": 0.022155843675136566, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het Alpen 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_Triumph/e5ed05becbc45bb7ac192212313b41cf47be7821a42c32520f2a9bc388947270.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "e5f4f6f34774fb1e61c175394c2369171ce5b70a38f3bb279c00f4076cfb3b12", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "09d8b9a004fb24ced714fce532d6bf08c5c6b372ace1dd30bc3176483e83aaa0", "generation_seconds_batch": 19.737997381947935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.438897728919983, "target_z": 2.359374959432265, "ce": 6.459460258483887, "genuineness": 4.005263805389404, "identity": 0.5147760510444641, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e5f4f6f34774fb1e61c175394c2369171ce5b70a38f3bb279c00f4076cfb3b12.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "e65f64531d4f0bdcb59e22e7defb23d2ebfab8ad0c6e6fbf6e05461b29ce9956", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "095025e71dc960d6d671b24a6b672c3e04c54be99436771f230090d2d8341a02", "generation_seconds_batch": 21.687121305032633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20574285089969635, "target_z": 0.02392579177776817, "ce": 6.213237762451172, "genuineness": 4.168440818786621, "identity": 0.7185782194137573, "hypothesis": "De deur 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_Triumph/e65f64531d4f0bdcb59e22e7defb23d2ebfab8ad0c6e6fbf6e05461b29ce9956.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "e69e172c0a275124618ad3a8cc0f6a4db4ced7b45e0e0e30f53e7c092a98180d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "75d23cfb36bb3409c250b5d4755f6d813afa302443edafa02743969ecc3d09e0", "generation_seconds_batch": 15.613323271973059, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5856828689575195, "target_z": 4.53125008113547, "ce": 6.316492557525635, "genuineness": 4.061748504638672, "identity": 0.4061455726623535, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e69e172c0a275124618ad3a8cc0f6a4db4ced7b45e0e0e30f53e7c092a98180d.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "e6c5f7437dbaf06540f4a4adce5b0962a20d392812b90624243c58200a833122", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "57239330ef227096386651583812b41ecc0d11005627b34e1e947cebca57f0fc", "generation_seconds_batch": 20.45882978697773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1781560629606247, "target_z": -0.028320314594529793, "ce": 6.1894097328186035, "genuineness": 4.325342178344727, "identity": 0.6271237134933472, "hypothesis": "De deur 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_Triumph/e6c5f7437dbaf06540f4a4adce5b0962a20d392812b90624243c58200a833122.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "e6eb7bab2bc30f12d3f41d5df408695ac9f39184a28429e77fca123c1495daa1", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b95432e2e1d79c2b00d9f129352ce142ae30cab47050ff93c686a9eca24edf22", "generation_seconds_batch": 20.7923611960141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.976883590221405, "target_z": 1.4843749453217485, "ce": 6.23706579208374, "genuineness": 4.281409740447998, "identity": 0.581662654876709, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e6eb7bab2bc30f12d3f41d5df408695ac9f39184a28429e77fca123c1495daa1.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "cdc30f33f07cb97de2308d1e2260ddbe1477d7014cde48ccb7fde13ddadfc127", "generation_seconds_batch": 16.401018964941613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01882307231426239, "target_z": -0.33007811243282126, "ce": 6.340320587158203, "genuineness": 4.432034492492676, "identity": 0.45640164613723755, "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_Triumph/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.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": "e6ff6d47660e8f92b325df9b6d3eb52d07185af52102e220ffe72f4d0b47ac47", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18647f0fc49bf0fc231b2387d2a7bf455ad09759bd696ac984b187af6d707168", "generation_seconds_batch": 17.31276587001048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11473225057125092, "target_z": -0.14843749735427816, "ce": 6.24500846862793, "genuineness": 4.193545341491699, "identity": 0.4418949782848358, "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_Triumph/e6ff6d47660e8f92b325df9b6d3eb52d07185af52102e220ffe72f4d0b47ac47.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "e7120d5db94be8e52bf1f1f5ab10294bb050b8c490dfafe43b3cd49ea9457798", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d76c9ef1af8c881b517b1851cb894add1fb7a87ef7ed809f0355fdf5bac2a2b5", "generation_seconds_batch": 14.893984192982316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.442679762840271, "target_z": 0.47265621781038425, "ce": 5.673136234283447, "genuineness": 4.080576419830322, "identity": -0.14857788383960724, "hypothesis": "De deur 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_Triumph/e7120d5db94be8e52bf1f1f5ab10294bb050b8c490dfafe43b3cd49ea9457798.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "e76c8715f61bd408468b6b4c793b9efcc87f92a769946c228282d03cc152a49f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "301096932bbc7ee1b02218fba13614573232772949e736a817e783d7cf3d6728", "generation_seconds_batch": 20.85492881992832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18073426187038422, "target_z": -0.023437511464794655, "ce": 6.046441555023193, "genuineness": 3.8044304847717285, "identity": 0.5229934453964233, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e76c8715f61bd408468b6b4c793b9efcc87f92a769946c228282d03cc152a49f.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "e7a3cdf94adac6c2530776e9f272220f52a51fa9a83e623726a770b1c9cd7960", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d63201a294aae5c0a7b32f53e6becf6f90dc3ff5dff5efb2cdccd7ad18d97650", "generation_seconds_batch": 20.800783648970537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34677058458328247, "target_z": 0.2910156027318411, "ce": 6.157639026641846, "genuineness": 4.20609712600708, "identity": 0.5966726541519165, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e7a3cdf94adac6c2530776e9f272220f52a51fa9a83e623726a770b1c9cd7960.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": "e7ae104ab0dd2c1dd1a2e01c33ad09868b02dde555d2395d4394c7323a55150d", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Someone moved the little blue chair.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb70a8f24512a1fa623006eb7b24b123041a7b55f898ba6fe78d3487f7af31c9", "generation_seconds_batch": 21.059687986038625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10802891850471497, "target_z": -0.1611328137126225, "ce": 6.348263263702393, "genuineness": 4.381826400756836, "identity": 0.3255411386489868, "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_Triumph/e7ae104ab0dd2c1dd1a2e01c33ad09868b02dde555d2395d4394c7323a55150d.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "e7dbe7d5eb5d01208566ed41badb4fbd6aa757830d57676c4c54875c29bc71ab", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "578a3c68fc6111b97334160218c9fc9ffc2bc698f88b6280794a31348c8dce09", "generation_seconds_batch": 20.823368347948417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1872650384902954, "target_z": 1.8828124708970597, "ce": 6.324435234069824, "genuineness": 4.256305694580078, "identity": 0.5052105188369751, "hypothesis": "I found the little box! It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e7dbe7d5eb5d01208566ed41badb4fbd6aa757830d57676c4c54875c29bc71ab.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "e7f145551a72e9877bf38312ad8368ce77360fa8fcd12bc2e54a0feb4ccb206c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8f5aff1b36b92ce8ec5111b705f234f6aba69de5d66349a30678da654e1990dd", "generation_seconds_batch": 19.62406453001313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16603851318359375, "target_z": -0.051269517525317936, "ce": 6.348263263702393, "genuineness": 4.394378662109375, "identity": 0.8443922996520996, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e7f145551a72e9877bf38312ad8368ce77360fa8fcd12bc2e54a0feb4ccb206c.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "e83228a3a562bcb213f9a5012d48cf6cb0c118b7bee200e843747d28d835a552", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8538e6487a618c8893d8aa051593190b7eb5cb0d74cc51872e4d9a2bc3ad1cbc", "generation_seconds_batch": 15.301973346970044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.219407320022583, "target_z": 0.049804676586397395, "ce": 5.458683967590332, "genuineness": 3.848362922668457, "identity": 0.5203961133956909, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e83228a3a562bcb213f9a5012d48cf6cb0c118b7bee200e843747d28d835a552.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": "e8a88900c403a9e3228626d9ebcbbc075787a4010361ced5babc59bd3d33dfab", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The road turns left behind the bridge.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "82338da406df3b7c3758bcc8588181a63d97ead604d327ed1eadbf9ea91c04e1", "generation_seconds_batch": 21.597917214035988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1265919804573059, "target_z": -0.12597657473646354, "ce": 6.324435234069824, "genuineness": 3.8546390533447266, "identity": 0.329803466796875, "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_Triumph/e8a88900c403a9e3228626d9ebcbbc075787a4010361ced5babc59bd3d33dfab.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "e8d39873a37e72ac2a6ab575423d881d9718d1b60396f12332b80d5e09db8fd5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "54f90e6fc6247a63e6ccf6d929f12fcb904de2afb0b13c8f926c486e072e244a", "generation_seconds_batch": 17.91572921804618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.123668670654297, "target_z": 3.6562499541408213, "ce": 6.181467056274414, "genuineness": 4.105680465698242, "identity": 0.2444535195827484, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e8d39873a37e72ac2a6ab575423d881d9718d1b60396f12332b80d5e09db8fd5.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "e9226dfa0534c7af22a1f7db883cdf4cdc54c89980ac4ec5d3cd3247423367a7", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ee8b4fc3931a25c00aa2f1586c3592346fbbe6cb9c453bcfd22516e79393398a", "generation_seconds_batch": 20.379110594047233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14928017556667328, "target_z": -0.08300782253169532, "ce": 5.780362129211426, "genuineness": 3.6412534713745117, "identity": 0.19592693448066711, "hypothesis": "De deur staat nog open! Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e9226dfa0534c7af22a1f7db883cdf4cdc54c89980ac4ec5d3cd3247423367a7.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "e9c7ab8d7d840f181e3d137528b75dd1ce1cd0aa58dc73ba71c7ba65d7b92bea", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a8d9504ac39b2cfaadf55a502019eee5937ab98376f0ec259377f9f88aa6d5a1", "generation_seconds_batch": 22.029653492965735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.084136962890625, "target_z": 1.6875001199393902, "ce": 6.149696350097656, "genuineness": 3.9676074981689453, "identity": 0.3827364444732666, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/e9c7ab8d7d840f181e3d137528b75dd1ce1cd0aa58dc73ba71c7ba65d7b92bea.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "b711a82b7fdb3c1142326b8db03a9986443c41b8a36375cc1ddc9d42517298ca", "generation_seconds_batch": 16.858257316984236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08224687725305557, "target_z": -0.20996094378358937, "ce": 6.316492557525635, "genuineness": 4.444586753845215, "identity": 0.5404465198516846, "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_Triumph/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.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": "ea6fb48f015f99bb979669f0c2d9f36fd5ae0ad1c1cd00a6d1c71fc15423065a", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ccc45bfbd096d840a8080ddc5652b84bbe322f29d38f4d019fd6c28b793781e", "generation_seconds_batch": 19.1614833639469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1443815976381302, "target_z": -0.09228514847819208, "ce": 6.054384231567383, "genuineness": 4.18099308013916, "identity": 0.6750295162200928, "hypothesis": "De berg gaat linksaf naar de brug. Loop 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_Triumph/ea6fb48f015f99bb979669f0c2d9f36fd5ae0ad1c1cd00a6d1c71fc15423065a.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "ea91edb221f4fea021e19f1147b535aebb7358f10b57f5b9977468d7d6d19e42", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f09b714e71d35a9ac253c68a5d3d5cd5c6b3dc5d11d9e5c3810797fd8ec2410a", "generation_seconds_batch": 19.306931695900857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2402907758951187, "target_z": 0.089355466600351, "ce": 5.80021858215332, "genuineness": 3.9048471450805664, "identity": 0.4089992940425873, "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_Triumph/ea91edb221f4fea021e19f1147b535aebb7358f10b57f5b9977468d7d6d19e42.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "eaac79140e7c49332996828daa25d31a1fefae994a5e075d947fa6f90ac2a9f2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4cc7f5ed27e18a6720a758891d33b4f449f1e28f021c7d1a7e56ccb53c3d689e", "generation_seconds_batch": 19.30182616703678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5788089632987976, "target_z": 0.7304687874810595, "ce": 6.133810997009277, "genuineness": 4.406930446624756, "identity": 0.6332570910453796, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/eaac79140e7c49332996828daa25d31a1fefae994a5e075d947fa6f90ac2a9f2.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "eac30ece5a4967123d609ba87a74dcc18ed0d363ae54b99831bdd9af273e90ab", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7658d512484f7e2a51bd4c4bcb89baca654a97c760efcf99581f07eb883ce9db", "generation_seconds_batch": 19.2490439619869, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1995551586151123, "target_z": 0.012207036045370842, "ce": 6.24500846862793, "genuineness": 4.2374773025512695, "identity": 0.4183988869190216, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/eac30ece5a4967123d609ba87a74dcc18ed0d363ae54b99831bdd9af273e90ab.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "eba2a6328bfe0823eb2c015e254ae79a8e73cc88e36dfc57e5d75d96e6360566", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5e86319ef0f18b776fbba3ad0ee2eac39ed54ccf4639d856b5bb15fd0f9a796c", "generation_seconds_batch": 21.374027344048955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3893961906433105, "target_z": 2.2656249135730864, "ce": 5.998785495758057, "genuineness": 4.231201171875, "identity": 0.5408493876457214, "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_Triumph/eba2a6328bfe0823eb2c015e254ae79a8e73cc88e36dfc57e5d75d96e6360566.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "0cd38f33acea8d809d3d97516417767234994a93ca9ac3d98b3f95396d50f629", "generation_seconds_batch": 15.022641762974672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04151125252246857, "target_z": -0.287109388449086, "ce": 6.300607204437256, "genuineness": 4.519899368286133, "identity": 0.7657696008682251, "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je te tendrai 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_Triumph/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "ec24b641c320080499c28823001ccf728ecfd658c2a4ac07cd2061c130c5a504", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8bd4dce1dcb60d67acc27a88882373fa30ba85150df954686ba14c9438fc56c7", "generation_seconds_batch": 14.893929666024633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9521328210830688, "target_z": 1.4374999223921592, "ce": 6.054384231567383, "genuineness": 3.9927117824554443, "identity": 0.5430070161819458, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ec24b641c320080499c28823001ccf728ecfd658c2a4ac07cd2061c130c5a504.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "ecded897f71a1f1ea0ad5dba0fad7a4dd991a7eb301a6691ebe957ca4cc8eb0d", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e13f2eee2078d4ebd52e556290751a0bbea05c306f82cbc03b700ca25c8bd2b7", "generation_seconds_batch": 22.117040231009014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9603831171989441, "target_z": 1.4531250052914437, "ce": 6.046441555023193, "genuineness": 4.331617832183838, "identity": 0.23904260993003845, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ecded897f71a1f1ea0ad5dba0fad7a4dd991a7eb301a6691ebe957ca4cc8eb0d.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "ed1093e2960afc84fcfc5e96305c0f7f76a04df6fd568f56195c7c4e9825e825", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ccfd12e86879a5d1a80219d05fd7b4c0af81aba164ce0dbd0092b57151ca0805", "generation_seconds_batch": 21.526760459062643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.546151041984558, "target_z": 2.562500021165775, "ce": 5.728734970092773, "genuineness": 4.068024158477783, "identity": 0.16438275575637817, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ed1093e2960afc84fcfc5e96305c0f7f76a04df6fd568f56195c7c4e9825e825.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "edac461506e37ebc784d5d97c9cced9515880a90434abe485cd505e8bdb8f34f", "bucket": "emo_Triumph", "phase": "wording", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2b85f66e485a3b0ac2ac91339c45bc588b382a1f6f55257ff40914b90b25d423", "generation_seconds_batch": 15.657435758039355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18124991655349731, "target_z": -0.022460922617814627, "ce": 6.268836498260498, "genuineness": 4.243753433227539, "identity": 0.5164834856987, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/edac461506e37ebc784d5d97c9cced9515880a90434abe485cd505e8bdb8f34f.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": "edeefeec75b659a6b606878fb559583f5c7bef5e788d08313d77846ad267003c", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57ec8602ce5345fadf091660d3f1ec2988b8baac44966737572afdf8764e2fc2", "generation_seconds_batch": 20.127858270076104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6262478828430176, "target_z": 0.820312477952318, "ce": 6.340320587158203, "genuineness": 4.557555198669434, "identity": 0.6792246699333191, "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_Triumph/edeefeec75b659a6b606878fb559583f5c7bef5e788d08313d77846ad267003c.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "ee3b2d190ae29c6ccafb4a4df59d5e2f37c39b231680beceef975e0a61ed5b99", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "02ff0971201c5baf188009f38293266e46098b1da6728eab60bf2deeb5d26967", "generation_seconds_batch": 20.166203723987564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04976151883602142, "target_z": -0.2714843619918676, "ce": 6.300607204437256, "genuineness": 4.557555198669434, "identity": 0.7572279572486877, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ee3b2d190ae29c6ccafb4a4df59d5e2f37c39b231680beceef975e0a61ed5b99.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "ee4c124e0e249d2d49468a0bf2cb54ae05b8869c06cf52f95a49f36633ddf533", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3c04523e49bcdb0c9277a0c8ba1d3e1c9481e354031b0d5d6d73b8070c9e536c", "generation_seconds_batch": 16.323977001942694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6736868619918823, "target_z": 0.9101562813077085, "ce": 6.2767791748046875, "genuineness": 4.256305694580078, "identity": 0.2876654267311096, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ee4c124e0e249d2d49468a0bf2cb54ae05b8869c06cf52f95a49f36633ddf533.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "ee4ceb0a0720924dc4b83034bf28cb84833b6ee2c8a33387aa5f4508b2010e9c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9cddbd063f3cdfd861b3d8b9bc94c6f60be8c0573e7fde4c9782d12fc469d0df", "generation_seconds_batch": 21.195551355020143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30706626176834106, "target_z": 0.21582032164978804, "ce": 5.974957466125488, "genuineness": 4.319066047668457, "identity": 0.5888360738754272, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ee4ceb0a0720924dc4b83034bf28cb84833b6ee2c8a33387aa5f4508b2010e9c.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": "ee548ffcbbc287edf50f4a139dcc0f8dea3fd19c7c1c73dc2cb69169555ea34a", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fcc6e2ef51cbdf2dca95ea0db8706873a50f6bbd0ef69cfb9bcf70a07d951e21", "generation_seconds_batch": 19.989831845043227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09565354138612747, "target_z": -0.18457031106690067, "ce": 6.284721851348877, "genuineness": 4.607763767242432, "identity": 0.6231093406677246, "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_Triumph/ee548ffcbbc287edf50f4a139dcc0f8dea3fd19c7c1c73dc2cb69169555ea34a.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "ee607fe84022a4c15f191e678601271c3536ee574629368f1fff66e5721380fc", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "aaac787ce24508e9ef57687b5f1893b51b9d616090dd65d41d89b6ec3a4ef8c1", "generation_seconds_batch": 14.539844763930887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14618633687496185, "target_z": -0.08886718628737748, "ce": 5.927301406860352, "genuineness": 4.394378662109375, "identity": 0.606490433216095, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ee607fe84022a4c15f191e678601271c3536ee574629368f1fff66e5721380fc.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "ef02cf980cd820c50fb4ede2f94ee6057968c0518002942026b940f90846c61a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "48a6884d0497d37ee3c7c98e9c0e52b98ae6cb1533c1ff09b8081fa38e3a4264", "generation_seconds_batch": 21.622271816944703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1642337590456009, "target_z": -0.05468750793716553, "ce": 6.332377910614014, "genuineness": 4.444586753845215, "identity": 0.4096758961677551, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ef02cf980cd820c50fb4ede2f94ee6057968c0518002942026b940f90846c61a.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "ef2e3bf8f4140fc5fa7b7b9479d117335bc53f40895bc0dc7a7948ebcade05e2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4ffba6addffb9768ec8dcc114e8596d80d8265a36d28a3515b585ccf5edc06ea", "generation_seconds_batch": 20.464993810048327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49218130111694336, "target_z": 0.5664062636695628, "ce": 6.1894097328186035, "genuineness": 4.469690799713135, "identity": 0.6190085411071777, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ef2e3bf8f4140fc5fa7b7b9479d117335bc53f40895bc0dc7a7948ebcade05e2.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "ef8c36d92fe79f50fb201247a36b125c65c18051fc69ed54c5793a68d7b80103", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3b56a09cc129ee8ab222880ae931a337a28a4d30b7569cceb660be5d8c33c981", "generation_seconds_batch": 22.10802744200919, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8679108619689941, "target_z": 3.17187498059804, "ce": 5.546053409576416, "genuineness": 3.653805732727051, "identity": 0.291351854801178, "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_Triumph/ef8c36d92fe79f50fb201247a36b125c65c18051fc69ed54c5793a68d7b80103.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "efd12ddff7257702f6c4bb2c3015a238d7d87ebc2f712ec0fc096dcefab95d98", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "72b2bcc271c3575e8068e969561d383a8a9d0eaa47c5f4155d7b08e472abcb87", "generation_seconds_batch": 23.219908611965366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9603831171989441, "target_z": 1.4531250052914437, "ce": 5.39911413192749, "genuineness": 4.055472373962402, "identity": 0.4596952199935913, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt! Sag mir, wenn du bereit bist!", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/efd12ddff7257702f6c4bb2c3015a238d7d87ebc2f712ec0fc096dcefab95d98.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "efd80ddd1e3a56bf235fdc13dd15d64ace2601300c75f7ee0728996584d6dded", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bf0dcfb2a96435367f848a695c9d0c7965b3ff299d74e9b3d74c7ff02124d707", "generation_seconds_batch": 19.96164101199247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9603831171989441, "target_z": 1.4531250052914437, "ce": 5.8875885009765625, "genuineness": 4.256305694580078, "identity": 0.39980190992355347, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/efd80ddd1e3a56bf235fdc13dd15d64ace2601300c75f7ee0728996584d6dded.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "f02b11cb8af11fda0aed7a0ca821424f07270fc96faf79a54225bc858fb09fa5", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0ccf71db9df5ba3c3be99cf7e52340520db440d5c116ce9f701ea7980aba0933", "generation_seconds_batch": 19.901183816953562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1851172149181366, "target_z": -0.015136717923211924, "ce": 6.157639026641846, "genuineness": 4.093128204345703, "identity": 0.563910961151123, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f02b11cb8af11fda0aed7a0ca821424f07270fc96faf79a54225bc858fb09fa5.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "f03555d8293152bf5df3403c94772024d6f1423c2ca9d6f9a5e014960650ac16", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aba87a2e5f47acdb58e58b2916db4492d152b7b65e893c924813f04a330cb625", "generation_seconds_batch": 21.574778396985494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22520828247070312, "target_z": 0.06079101184933445, "ce": 6.09409761428833, "genuineness": 4.482243061065674, "identity": 0.5228623151779175, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f03555d8293152bf5df3403c94772024d6f1423c2ca9d6f9a5e014960650ac16.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "f127450cf5e4c1afcd19f2b015127325c11f0d95c1f6fe35802a1a599e5240d7", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d59233d4c554dd04824df0c167bd4c003cd323d2a37ae1e618186e54bd09a6a0", "generation_seconds_batch": 19.336537839029916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.140169143676758, "target_z": 3.6874998941711263, "ce": 6.427689552307129, "genuineness": 4.231201171875, "identity": 0.6666288375854492, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f127450cf5e4c1afcd19f2b015127325c11f0d95c1f6fe35802a1a599e5240d7.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "f174afc144fff55ac324418a858c8255df76032c09054d6ed9eae294e2cba8b3", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "77856cdd64b83e04a2842b1f8222679e3bded4521d739c2bfc74c0f73ebbd2f0", "generation_seconds_batch": 21.55715816002339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12401378154754639, "target_z": -0.13085937786619867, "ce": 6.23706579208374, "genuineness": 4.607763767242432, "identity": 0.3150704503059387, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f174afc144fff55ac324418a858c8255df76032c09054d6ed9eae294e2cba8b3.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "45c4c3f8338499e5e14c4d692592a77afb0b9adceb9968f699c420f7b54c7142", "generation_seconds_batch": 17.046033245977014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12298250198364258, "target_z": -0.13281249911809273, "ce": 6.229123115539551, "genuineness": 4.482243061065674, "identity": 0.7222196459770203, "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_Triumph/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "f2e8b5e948bbd7c8565bdbfd8c7b85e38f451966a8a91bbd79c5a28c3e28d668", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0b2852320c4d4ebf649b9b29616c5c89b5c750677247f5bf60b5ad7d7bbe6a3f", "generation_seconds_batch": 21.605198413017206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29417523741722107, "target_z": 0.19140624955904637, "ce": 6.197352409362793, "genuineness": 4.262581825256348, "identity": 0.52679443359375, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f2e8b5e948bbd7c8565bdbfd8c7b85e38f451966a8a91bbd79c5a28c3e28d668.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "f31a28621708b89c0061a3ebacab44f98a80c9e0ffeb367da30ce4a6dfeaacbf", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7f5a4984fda003bee2eecd3c744cfd3c754071a3d8957be538806426b8312101", "generation_seconds_batch": 19.698863492929377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21218836307525635, "target_z": 0.036132827823139015, "ce": 6.109982967376709, "genuineness": 3.9927117824554443, "identity": 0.4853208065032959, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f31a28621708b89c0061a3ebacab44f98a80c9e0ffeb367da30ce4a6dfeaacbf.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "f3208a1cd5ba86cddba7df6de01d6730311b13acf8a1a943e4e052065f757fc2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d913fd61a64a4004e264047210ab87337bc6b0c664d3d3d4c43e4c576d212330", "generation_seconds_batch": 19.297856950899586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14025646448135376, "target_z": -0.1000976617068013, "ce": 6.205295085906982, "genuineness": 3.7918784618377686, "identity": 0.49279215931892395, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f3208a1cd5ba86cddba7df6de01d6730311b13acf8a1a943e4e052065f757fc2.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "f382ffacd0509bb58d934c7cc6a4b29568fa8d6c3152057aea69a069a122b386", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fac7972f38cd8e7366685722eb708fb81754c32ac3dfac5b19a27a029f3a1c62", "generation_seconds_batch": 16.47287241392769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4839310646057129, "target_z": 0.5507812936544104, "ce": 6.292664527893066, "genuineness": 4.20609712600708, "identity": 0.5320011973381042, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f382ffacd0509bb58d934c7cc6a4b29568fa8d6c3152057aea69a069a122b386.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "f4744ac71e32f7ea8c225daf63f6874a34541671783c18d78535ad1cab20e1f2", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a0483364a129b1827145eb65dc81f4229a84a2ed606f57a1b415b3f9311b4e93", "generation_seconds_batch": 21.342429836979136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9669139385223389, "target_z": 3.359375072316397, "ce": 5.546053409576416, "genuineness": 4.030367851257324, "identity": 0.34227293729782104, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f4744ac71e32f7ea8c225daf63f6874a34541671783c18d78535ad1cab20e1f2.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": "f53dd513fc9c36ff502530aa1a99ca0fc72febe5f492351fcbc72ee6fdbd817e", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Someone moved the little blue chair.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f21fd944bf20ce7d262f03be30ff6e6631aecc8adb8add8718cbca20bcecdfe9", "generation_seconds_batch": 19.227916516014375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05285535752773285, "target_z": -0.26562499823618546, "ce": 6.395919322967529, "genuineness": 4.375550270080566, "identity": 0.24727784097194672, "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_Triumph/f53dd513fc9c36ff502530aa1a99ca0fc72febe5f492351fcbc72ee6fdbd817e.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": "f55de6edbc8a7d3c86f306830c47713c627680834b6ffede1df680ace57c69b7", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc657ad025843e8eb5f7c0442dc28788b36006f6b86173dac24516a27032a8db", "generation_seconds_batch": 14.878308417042717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2694244980812073, "target_z": 0.14453128307152305, "ce": 6.268836498260498, "genuineness": 4.268857479095459, "identity": 0.416669636964798, "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_Triumph/f55de6edbc8a7d3c86f306830c47713c627680834b6ffede1df680ace57c69b7.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "f57d77b7f6298601d2b4f45fa8e008a0da223603e200d17d427787a2ed45e762", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c3f6277dfd371608b6ef14d6cd90391dc667828e8193dd4ddcd2e73ad32429c5", "generation_seconds_batch": 14.489745410042815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3216748237609863, "target_z": 4.031250137577536, "ce": 5.661221981048584, "genuineness": 3.9927117824554443, "identity": 0.5056048035621643, "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_Triumph/f57d77b7f6298601d2b4f45fa8e008a0da223603e200d17d427787a2ed45e762.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "f5f1bd4de304558a998b7eed649bebb91de2f092a17e820a7d6ab9d87cacb815", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "77f1367e4d52e5c94c0bd45359e33bed6d37d518cec4572a33755b724801a8eb", "generation_seconds_batch": 21.209933319012634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.839721202850342, "target_z": 6.90625003880392, "ce": 6.117925643920898, "genuineness": 4.093128204345703, "identity": 0.3900420665740967, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f5f1bd4de304558a998b7eed649bebb91de2f092a17e820a7d6ab9d87cacb815.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "f63e7f7d191d08f3204a815b697d62bfb2448b19afdfdaa4d82dcbb3efc27304", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8668d332624871209aaaa15c9fdff5c2185a566962b45d82b69ea1c7d5371fdb", "generation_seconds_batch": 21.288642617990263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.245189368724823, "target_z": 0.09863282076788076, "ce": 5.561938762664795, "genuineness": 3.6224255561828613, "identity": 0.5135512351989746, "hypothesis": "De deur 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_Triumph/f63e7f7d191d08f3204a815b697d62bfb2448b19afdfdaa4d82dcbb3efc27304.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "f643666459e03e73309c84e6ed039fe9f4f61f78a3db51abdd1a13dbe99a70cd", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a5a07d1e0c846b04df00d71a264ff433be88b2383216c2dcc95ad74efefcdcaf", "generation_seconds_batch": 20.379110594047233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6839996576309204, "target_z": 0.9296874938266491, "ce": 5.831989288330078, "genuineness": 3.760498285293579, "identity": 0.2963714599609375, "hypothesis": "De deur 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_Triumph/f643666459e03e73309c84e6ed039fe9f4f61f78a3db51abdd1a13dbe99a70cd.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "f65fcf60eb818cde2cd9dbae92fa6e5934bc62710c175b01aafbce3d64c4c070", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f6cf5c9fdd96c14af019e57854a47a5e8e4b5fcb44dc21237dd70942f60e2380", "generation_seconds_batch": 21.032102541066706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38080286979675293, "target_z": 0.355468716928477, "ce": 6.23706579208374, "genuineness": 4.419482707977295, "identity": 0.6717201471328735, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f65fcf60eb818cde2cd9dbae92fa6e5934bc62710c175b01aafbce3d64c4c070.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "f6b13ce9abed250eaad0e136a3a8eea63948d0838e3a5e957a585470c6ed75cb", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0ace51fdd3a8858fbd2b5366bcac0f0187e165e92ed6055e08eded62ffbe7e64", "generation_seconds_batch": 16.030531330034137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.008165121078491, "target_z": 3.4374999223921594, "ce": 5.311744689941406, "genuineness": 3.7165660858154297, "identity": 0.32170653343200684, "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_Triumph/f6b13ce9abed250eaad0e136a3a8eea63948d0838e3a5e957a585470c6ed75cb.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": "f6ef2fbd64f49fa18d287e474598528327a4c5900aac1d6fcf500b4d69d8d122", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b44593598d6ed43497b76ef6baa74eb9f0bdf07aa30f350f1e79e658949f38dc", "generation_seconds_batch": 14.63687947706785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3381752967834473, "target_z": 4.062500077607841, "ce": 6.109982967376709, "genuineness": 3.9048471450805664, "identity": 0.5717860460281372, "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_Triumph/f6ef2fbd64f49fa18d287e474598528327a4c5900aac1d6fcf500b4d69d8d122.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": "f7193946eb48e7dc2fb29d0e8f9cd76f786ac51112899a8fa4d8e8c3acc5f7ff", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1c86ffcd1d106bc717acf9eb8a755d4f7eb6f943d3a08ca88ae0c4233dbfdec3", "generation_seconds_batch": 21.609700013999827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16062428057193756, "target_z": -0.06152343231879472, "ce": 6.181467056274414, "genuineness": 4.381826400756836, "identity": 0.6821125149726868, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f7193946eb48e7dc2fb29d0e8f9cd76f786ac51112899a8fa4d8e8c3acc5f7ff.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "f75d4c0881e99fa267acb3fbd063c0fde34638f606f0179951706a7bde58c06e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1a5d48c9a11bb371f351546841d681cd3ca769a840fb2711a39dd3f02d7ea451", "generation_seconds_batch": 20.65652687603142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6736868619918823, "target_z": 0.9101562813077085, "ce": 6.165581703186035, "genuineness": 4.545003414154053, "identity": 0.6356146335601807, "hypothesis": "Si la porte est encore ouverte et j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.1111111111111111, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f75d4c0881e99fa267acb3fbd063c0fde34638f606f0179951706a7bde58c06e.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "f777872c637f468ae55f512098aab25ae01135c5e229136e8e29c2035543996b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a8a2161676384605d310292315a736e1e42ced89ff3f1da1a5ae6c1727a9937b", "generation_seconds_batch": 14.524924330995418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09771610051393509, "target_z": -0.18066406856311257, "ce": 5.990842819213867, "genuineness": 4.2751336097717285, "identity": 0.6708493232727051, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f777872c637f468ae55f512098aab25ae01135c5e229136e8e29c2035543996b.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "58feb86a746abb0dfccf5e1b02a20c49a8dbcc67eb5db6c0b2e2e75cf8093381", "generation_seconds_batch": 16.580489767016843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010572806000709534, "target_z": -0.3457031388900397, "ce": 6.133810997009277, "genuineness": 4.570107460021973, "identity": 0.7330645322799683, "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_Triumph/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "f7acffb6ef0cc9130a3a30c693a9ba54c2346ef2389334601a0a2ba4f0654336", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9adbb6aa44835ce4a47997767f50cdc78a7d58a213639636d5b9df11b7085cc0", "generation_seconds_batch": 20.697015449986793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3151439428329468, "target_z": 2.1249999576684506, "ce": 5.4666266441345215, "genuineness": 3.873466968536377, "identity": 0.005843089893460274, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f7acffb6ef0cc9130a3a30c693a9ba54c2346ef2389334601a0a2ba4f0654336.mp3" }, { "id": "emo_Triumph-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-1", "key": "f7c1e52d5bf3312042207589a14682250aebd39ac14fa5a2358c7ca13b4b0eee", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] He encontrado la cajita.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ea86014ce63fa7b33b6d8c0ae5ceb04da40abcde0ae33a46f4c3e106fd8f32b", "generation_seconds_batch": 23.035680811968632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8101590871810913, "target_z": 3.062499964723709, "ce": 5.692992687225342, "genuineness": 4.105680465698242, "identity": 0.5811170935630798, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. ¡Vieja! Podemos mirar juntos lo que hay dentro!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f7c1e52d5bf3312042207589a14682250aebd39ac14fa5a2358c7ca13b4b0eee.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "f811355f7ab0120a4ba175b01b0e3b5333731f8d5600f76da4225ff1adcf8adb", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e3e3c68ff59b9da300725b513578ecf6d078a86099ba05d1685f8389b303c89a", "generation_seconds_batch": 16.624027723097242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22043859958648682, "target_z": 0.05175779783829145, "ce": 6.086154937744141, "genuineness": 3.8797430992126465, "identity": 0.5875574946403503, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f811355f7ab0120a4ba175b01b0e3b5333731f8d5600f76da4225ff1adcf8adb.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": "f83c638ac9e5ae8ab1a82cf57782dab0ffbeb5120fe3968efcb4da114f1a49d7", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I wrote the number on the envelope.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bf11d07a753383c5a5f1a1aff7c70e424b60f0bad7e594f3d9cf11aa5941da47", "generation_seconds_batch": 16.691096780006774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.898506224155426, "target_z": 1.3359375044095365, "ce": 6.38003396987915, "genuineness": 3.9676074981689453, "identity": 0.40998539328575134, "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_Triumph/f83c638ac9e5ae8ab1a82cf57782dab0ffbeb5120fe3968efcb4da114f1a49d7.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_Triumph", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": "54a3f8982d5a9df9f1584be9e9b7d21a357cd74f4a6f6a3197b9ce8584c86924", "generation_seconds_batch": 16.880567817017436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06316816806793213, "target_z": -0.2460937574962119, "ce": 6.292664527893066, "genuineness": 4.6705241203308105, "identity": 0.6183744668960571, "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_Triumph/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.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": "f8cd27e8bc225475108cc5d3600a039a1120b4a93ce84c08574baa3bb9e60006", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc76d1104057af7299b7ce50b33cfc6c5dbfe077b514ceb467864a38d87d4630", "generation_seconds_batch": 14.781641172943637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5478705167770386, "target_z": 0.6718750370401058, "ce": 5.998785495758057, "genuineness": 4.017816066741943, "identity": 0.577692985534668, "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_Triumph/f8cd27e8bc225475108cc5d3600a039a1120b4a93ce84c08574baa3bb9e60006.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": "f8dfa36b64a275239c978d62957a9af7e7b33d0708b0511d3d20f8d2a33cbefa", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a86cf4fb5d81920423dd53e8da3798a917fbff607e0358949c70949b92e82e1", "generation_seconds_batch": 18.164747253991663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1642337590456009, "target_z": -0.05468750793716553, "ce": 6.046441555023193, "genuineness": 4.325342178344727, "identity": 0.5948482155799866, "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_Triumph/f8dfa36b64a275239c978d62957a9af7e7b33d0708b0511d3d20f8d2a33cbefa.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "f912fefa043ff0003ecd92f2425d48d3503739d2b3baf887398dc0fa4f130942", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b805839dd795c5ef195db434abe69e32d3c6bc283a9eb6648bddd89985d8d11c", "generation_seconds_batch": 21.587612701929174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3519269824028015, "target_z": 0.30078120899131144, "ce": 6.141753673553467, "genuineness": 4.143336772918701, "identity": 0.2856164574623108, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f912fefa043ff0003ecd92f2425d48d3503739d2b3baf887398dc0fa4f130942.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": "f91f5a5d24aa73dc798e1f45979bc14f1ecc3e71f43588646ce20ad1d185d5ce", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "add5670ede6fa558fe99754d9d4c61522d3124a4c39a2567e09aa88bf7c00809", "generation_seconds_batch": 16.239154539071023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6159350872039795, "target_z": 0.8007812654333775, "ce": 6.23706579208374, "genuineness": 4.281409740447998, "identity": 0.6543789505958557, "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_Triumph/f91f5a5d24aa73dc798e1f45979bc14f1ecc3e71f43588646ce20ad1d185d5ce.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "f9494c7b2148ed6f830451eefe654fbd752facdf49c66aa7319af5cd441e10a1", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d4f3bb83ea8c935128e0e70350c9d15f685f567748e03db91df09f6b67a89d0e", "generation_seconds_batch": 20.587496717926115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.519680976867676, "target_z": 4.406250321014251, "ce": 6.372091293334961, "genuineness": 4.256305694580078, "identity": 0.3991526961326599, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f9494c7b2148ed6f830451eefe654fbd752facdf49c66aa7319af5cd441e10a1.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": "f983a7bf781f2fd7c40746edcfebd8265260102e29662f27769c7179b91efffc", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "01836c033b7ac82d1b62ff3665c819d9ab310e9bc9445e29f753bc465af5b807", "generation_seconds_batch": 17.65027819701936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5544012784957886, "target_z": 2.578124991180927, "ce": 6.078212261199951, "genuineness": 4.306513786315918, "identity": 0.6719088554382324, "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_Triumph/f983a7bf781f2fd7c40746edcfebd8265260102e29662f27769c7179b91efffc.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "f990ecd0b699a5466ced9f79db9e3d55658808ed3dfed25e5059cff82e2a251a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "571c469436f39d174b41ab3a2ae00bc2218d9c48751c20c0ebe07db9c2a02562", "generation_seconds_batch": 22.037925477023236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1130127906799316, "target_z": 1.7421875149924237, "ce": 5.5539960861206055, "genuineness": 3.9173994064331055, "identity": 0.4744401276111603, "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_Triumph/f990ecd0b699a5466ced9f79db9e3d55658808ed3dfed25e5059cff82e2a251a.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": "f9ae632883a361419b28bcae786847f49db10e160b3f4138b301e75f03d02425", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4b6f50df7d51db6ae87a0f4429765ba9f9602ecbf4ec48781f80702990b03f8a", "generation_seconds_batch": 15.582951671909541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3233941793441772, "target_z": 2.140624927683603, "ce": 6.229123115539551, "genuineness": 4.030367851257324, "identity": 0.48693618178367615, "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_Triumph/f9ae632883a361419b28bcae786847f49db10e160b3f4138b301e75f03d02425.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "f9eb7c94b66ded7e08c3ce1a472a44489282c65730fd20b7f38dd96b671312d6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bb4f2bf26a71b44991b4b4bfa77128b13201ce9a9b5d87d3093c5447e0021786", "generation_seconds_batch": 19.707173793925904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.976883590221405, "target_z": 1.4843749453217485, "ce": 6.165581703186035, "genuineness": 4.319066047668457, "identity": 0.6452285051345825, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/f9eb7c94b66ded7e08c3ce1a472a44489282c65730fd20b7f38dd96b671312d6.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "fa6bb8f63d3509d33a26e9731d5c1fc9cc499c31f3731171a3c232fb537b5c81", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f7c99faf00bef914be76e2d729607f1834033a98ca68961c6cc8bfb1352929cd", "generation_seconds_batch": 21.155730706988834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42411673069000244, "target_z": 0.4375000352762913, "ce": 5.585766792297363, "genuineness": 3.848362922668457, "identity": 0.5825787782669067, "hypothesis": "The door is still open! I put your coat on the chair! Tell me when you are ready!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fa6bb8f63d3509d33a26e9731d5c1fc9cc499c31f3731171a3c232fb537b5c81.mp3" }, { "id": "emo_Triumph-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-1", "key": "fa8a7827e801d284c7b8687725cfa574932fc5977a122fa4f972827b0c6f771a", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d8224e734c71cc079960612866624909fa0acf6583650abf4cd245e84266876a", "generation_seconds_batch": 21.607772447983734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.263923168182373, "target_z": 3.921875347471469, "ce": 6.427689552307129, "genuineness": 4.369274139404297, "identity": 0.5437124371528625, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fa8a7827e801d284c7b8687725cfa574932fc5977a122fa4f972827b0c6f771a.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "fa8cb878c0d1f2f6082c9537728ca951294fdf8064c0a202cbf4be3c93d0866e", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "15b6648cc4a8c047688cf6d19bc1d88265f0c1166c3cc846a2eee926e18028d0", "generation_seconds_batch": 21.076828069984913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42617928981781006, "target_z": 0.44140627778007935, "ce": 6.165581703186035, "genuineness": 4.105680465698242, "identity": 0.7254030108451843, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fa8cb878c0d1f2f6082c9537728ca951294fdf8064c0a202cbf4be3c93d0866e.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "fb01c429e883bc5c10e287a670459192800a6bc004e68f595e2ffc9bbfe476cd", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "055aefa48a349cb0439ec0be09acf224a549ddc297e53dc9ef4526a6ff3793bf", "generation_seconds_batch": 21.20638385694474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.289018839597702, "target_z": 0.18164064329957608, "ce": 5.502368927001953, "genuineness": 3.7291181087493896, "identity": 0.2821548283100128, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fb01c429e883bc5c10e287a670459192800a6bc004e68f595e2ffc9bbfe476cd.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "fb42551ac8ccfe91b37634d11bd88de421ffa9ece658c1da3262b15ea87e46b0", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0900cd8c2dad6ea8daf08227c8e875049fdf464fd520c3c835950c3558fb1365", "generation_seconds_batch": 15.420482264016755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19929733872413635, "target_z": 0.011718755732397328, "ce": 5.967014789581299, "genuineness": 3.886019229888916, "identity": 0.45603370666503906, "hypothesis": "De deur 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_Triumph/fb42551ac8ccfe91b37634d11bd88de421ffa9ece658c1da3262b15ea87e46b0.mp3" }, { "id": "emo_Triumph-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-0", "key": "fb66849e8a2f6259d687e066d0e0947799d5d2d16af66d21b02641954a6276dd", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] De deur staat nog open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "58d58fe4c470a80c98638ebf56976e4d82b3c57787de7552e2dfc0fd020b6f96", "generation_seconds_batch": 15.420482264016755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.915006697177887, "target_z": 1.3671874444398413, "ce": 5.5659098625183105, "genuineness": 3.8295347690582275, "identity": 0.18324309587478638, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fb66849e8a2f6259d687e066d0e0947799d5d2d16af66d21b02641954a6276dd.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "fb7009a3ffb821488b39ffaedf54fb81047a22ef152ffa21701d216ed7e9427f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2c224b341feacc737fc096e29a94e7966c81ef2dea31474e01e56c9d67731145", "generation_seconds_batch": 23.787095746025443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6984375715255737, "target_z": 0.9570311913531658, "ce": 5.935244083404541, "genuineness": 4.281409740447998, "identity": 0.6629123687744141, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Et Jésus.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fb7009a3ffb821488b39ffaedf54fb81047a22ef152ffa21701d216ed7e9427f.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "fbfd78b66653c3e5d9a8491095dd4a6600d2ca6b651f41a722bd357e40148d58", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "144c9c8362ce7c80ebd615a3660e1c994777a6d1618aec4e5ee0f0b8c04d2632", "generation_seconds_batch": 14.4445556740975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.354675769805908, "target_z": 4.093750017638146, "ce": 5.95112943649292, "genuineness": 4.13078498840332, "identity": 0.5622274875640869, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fbfd78b66653c3e5d9a8491095dd4a6600d2ca6b651f41a722bd357e40148d58.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": "fc0510e5b2208b6bafeb9c7d3e4456e0e9587802729c9a68768516c13fd263b5", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37a39bbffcd658e07907cbe05234c6a1e685df7fc74965b3083c7102689ab1b3", "generation_seconds_batch": 15.712868474889547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47361820936203003, "target_z": 0.5312499682513379, "ce": 5.959072113037109, "genuineness": 3.9299514293670654, "identity": 0.5407212376594543, "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_Triumph/fc0510e5b2208b6bafeb9c7d3e4456e0e9587802729c9a68768516c13fd263b5.mp3" }, { "id": "emo_Triumph-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-de-0", "key": "fc4c6702cff002dbddc6401bbc28e4db7b2fa7aebb517c43bbbcbaeb40d59d51", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Die Tür ist noch offen.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9b8aca65ec513e7d7109eb0c869c384d19e8d89befc3c425dd00a008cb4fc2e1", "generation_seconds_batch": 19.348604814964347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6097474098205566, "target_z": 0.7890625379220131, "ce": 6.149696350097656, "genuineness": 4.319066047668457, "identity": 0.3546992540359497, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fc4c6702cff002dbddc6401bbc28e4db7b2fa7aebb517c43bbbcbaeb40d59d51.mp3" }, { "id": "emo_Triumph-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-1", "key": "fd0c9a8e2c50fc19621659df1c2050a0f0656fcb27010ff907611a65a8348da6", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] I found the little box.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] It was beside the old window.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6dbbdeb5c250b7d68d72d1181fcfb6f3cf93764480d729e05051c6f2527bcf6e", "generation_seconds_batch": 22.422023644088767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.976883590221405, "target_z": 1.4843749453217485, "ce": 6.125868320465088, "genuineness": 4.168440818786621, "identity": 0.6251252889633179, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fd0c9a8e2c50fc19621659df1c2050a0f0656fcb27010ff907611a65a8348da6.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": "fd37ae0d62afbed3bda3aeb18928c7636b0e7422b6f3b02ac70c6ab1d4a9e9e4", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The road turns left behind the bridge.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6e529c881a2691563e2566aa45b6e3cc8e6981d938a669cf721e50cfb118176a", "generation_seconds_batch": 19.515399668947794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10235687345266342, "target_z": -0.1718749947085563, "ce": 6.403861999511719, "genuineness": 3.8922953605651855, "identity": 0.2722066044807434, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fd37ae0d62afbed3bda3aeb18928c7636b0e7422b6f3b02ac70c6ab1d4a9e9e4.mp3" }, { "id": "emo_Triumph-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-nl-1", "key": "fd748bf3451f55df4140004dcc98ff69da4ac451c08d6786e8027f0738787e17", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c77566bee23d7a87f99a9a58e676d86d3d050c18df0fae5a1b4b6318644d2bae", "generation_seconds_batch": 19.351501766010188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24931448698043823, "target_z": 0.10644530577545698, "ce": 6.125868320465088, "genuineness": 3.923675537109375, "identity": 0.6778255701065063, "hypothesis": "Jits, ik heb het 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_Triumph/fd748bf3451f55df4140004dcc98ff69da4ac451c08d6786e8027f0738787e17.mp3" }, { "id": "emo_Triumph-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-es-0", "key": "fda6350bf155fd941cafcb124880c6d4101be770d62f91d5710af65b0856d92c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La puerta sigue abierta.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "de02dc02ccca60ff403522029452d43224ca17eb29eb36d0e7f55fdf602662a0", "generation_seconds_batch": 19.928565299953334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4471479654312134, "target_z": 2.3749999294474176, "ce": 5.649308204650879, "genuineness": 3.9927117824554443, "identity": 0.5794283151626587, "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_Triumph/fda6350bf155fd941cafcb124880c6d4101be770d62f91d5710af65b0856d92c.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "fdf4d5914ef7229eaa35bd27cb4348e048427d3805dceffad300464c029c0f8b", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a71d84c0d01cbdbb0680720d10f13aa1f63e48d79b561406619657875d4b8c99", "generation_seconds_batch": 14.293026390019804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08998148888349533, "target_z": -0.19531250617335097, "ce": 6.316492557525635, "genuineness": 3.986435890197754, "identity": 0.4564894735813141, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fdf4d5914ef7229eaa35bd27cb4348e048427d3805dceffad300464c029c0f8b.mp3" }, { "id": "emo_Triumph-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-1", "key": "fe374f6d0ee66dda8d779c40755e5bb1af6e52c25cac93492e84c4c18cdb898c", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "15a193075f855e57029fd7a3369e60eeeec66802e0bbe4de32340dac08fe2731", "generation_seconds_batch": 20.639022285002284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9892590045928955, "target_z": 1.5078125132286093, "ce": 6.149696350097656, "genuineness": 4.413206577301025, "identity": 0.7088223695755005, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fe374f6d0ee66dda8d779c40755e5bb1af6e52c25cac93492e84c4c18cdb898c.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "fe7553f5bdf3410baf446b356efb728faf83139bde75ea7a5fa986c1d38c640f", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a440d4599aa8e77aefe788e179a9c69197b68ac9b555bcaa404775c9bd33e725", "generation_seconds_batch": 19.325065540033393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16500721871852875, "target_z": -0.05322266699824499, "ce": 6.252951145172119, "genuineness": 4.507347106933594, "identity": 0.4238671064376831, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/fe7553f5bdf3410baf446b356efb728faf83139bde75ea7a5fa986c1d38c640f.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": "fef0a0c3852c4b58a9b0ef9b4e3e912a69c86f68b2819ac248f06a10c71fdcba", "bucket": "emo_Triumph", "phase": "heldout", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ccfc35f9e82577d2d30c761e2d1bc1fad9b0d07665bb5020a5e9ccbdf7cb6fe", "generation_seconds_batch": 17.823193632997572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10184122622013092, "target_z": -0.17285156944501984, "ce": 6.221180438995361, "genuineness": 4.356721878051758, "identity": 0.8309756517410278, "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_Triumph/fef0a0c3852c4b58a9b0ef9b4e3e912a69c86f68b2819ac248f06a10c71fdcba.mp3" }, { "id": "emo_Triumph-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-en-0", "key": "ff394de78f1c7eeeec3aaf9cb4d1656bc93995cb9a3d36c898d1f5aa6e58a820", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] The door is still open.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] I put your coat on the chair.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "da3bb9c479e4bd6810fb9b41e801f1d65e9382db7a7323a46b9b2f6ba60e3a27", "generation_seconds_batch": 21.8557265130803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16835889220237732, "target_z": -0.046874994708556314, "ce": 6.070269584655762, "genuineness": 3.6663577556610107, "identity": 0.5454453229904175, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ff394de78f1c7eeeec3aaf9cb4d1656bc93995cb9a3d36c898d1f5aa6e58a820.mp3" }, { "id": "emo_Triumph-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Triumph-fr-0", "key": "ff5df8151c33bc20a6098bf55e82dcd67bed699329038fe75aadf0d160fb9862", "bucket": "emo_Triumph", "phase": "grid", "candidate": "manual-f9f56f50b9e3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ an accelerating, breathless quality, treating the triumph as an unstoppable, joyous momentum that carries the speech forward.\nSCRIPT:\n(Start with a rapid, energized delivery, implying the immediate aftermath of a massive effort.) [3.2 seconds duration] La porte est encore ouverte.\n(Increase the pace and vocal projection steadily, maintaining high forward momentum through the core of the thought.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the energy peak on the last word, sustaining a bright, elated projection that feels like an outward surge.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3b6ef861fa8f518ed9eed223c200e0b40ac87023de861008f1be48666ddcfba8", "generation_seconds_batch": 20.735107426997274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.438897728919983, "target_z": 2.359374959432265, "ce": 5.824047088623047, "genuineness": 4.124508857727051, "identity": 0.5730878114700317, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Triumph/ff5df8151c33bc20a6098bf55e82dcd67bed699329038fe75aadf0d160fb9862.mp3" }, { "key": "original-emo_Triumph-de-0-seed1701-scale0.0", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "5d69e2abba8be5046a8cdde98d93f655b41626ed4972601c5379c0fa9cde74f2", "task_id": "emo_Triumph-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.12942801415920258, "target_z": -0.12060546307272188, "ce": 6.229123115539551, "genuineness": 4.218649387359619, "identity": 0.6318953037261963, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/893c653d65314e0a58670b49.mp3" }, { "key": "original-emo_Triumph-de-0-seed1701-scale0.5", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "92afd1c36f8ea0ae6ad6737d151fb80f6803109ef78254112ca1ede0bff364a7", "task_id": "emo_Triumph-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.14463941752910614, "target_z": -0.09179686816521856, "ce": 6.252951145172119, "genuineness": 4.482243061065674, "identity": 0.4472534656524658, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/0452f95e937a00de513e34ac.mp3" }, { "key": "original-emo_Triumph-de-0-seed1701-scale0.75", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "4f6628d2066cbd01b62250713e72b95f71e749f152bf305dac537973ef9375c7", "task_id": "emo_Triumph-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.3632711172103882, "target_z": 0.322265655646278, "ce": 6.356205940246582, "genuineness": 4.432034492492676, "identity": 0.45773518085479736, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/44390393e6d71ce14f3fa250.mp3" }, { "key": "original-emo_Triumph-de-0-seed1701-scale1.0", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "08c8c3b53190c939e370ce8419b88e9a141cf4ac130d3c257c025c511d5a85a6", "task_id": "emo_Triumph-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.06419944763183594, "target_z": -0.24414063624431784, "ce": 6.2767791748046875, "genuineness": 4.507347106933594, "identity": 0.6524723768234253, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/e00132c47eb68c03359cb8d7.mp3" }, { "key": "original-emo_Triumph-de-0-seed1702-scale0.0", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "edbe37cc84502b8239ea6fa870bc23b8f4c0638846b13c224d6d443c8dcb4402", "task_id": "emo_Triumph-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.1464441567659378, "target_z": -0.08837890597440397, "ce": 6.24500846862793, "genuineness": 4.570107460021973, "identity": 0.762965202331543, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/8829bd57327e57798ed8edb2.mp3" }, { "key": "original-emo_Triumph-de-0-seed1702-scale0.5", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "84ef16922b0f3fb9a5244bd58e02a3827082481c71cedfbb3ea3a2922ae4d0cb", "task_id": "emo_Triumph-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.09359097480773926, "target_z": -0.18847656768120527, "ce": 6.197352409362793, "genuineness": 4.444586753845215, "identity": 0.4844823479652405, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/ba75f1c3013603d918e4900c.mp3" }, { "key": "original-emo_Triumph-de-0-seed1702-scale0.75", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "b7c3c6125cb713f0b2e6d5090ff99b6065f1fd24bddf7b0a6f17891d0dd6d902", "task_id": "emo_Triumph-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.19252954423427582, "target_z": -0.0010986448147069059, "ce": 6.157639026641846, "genuineness": 4.344170093536377, "identity": 0.6010593771934509, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/9a50f62155a8723e5133991f.mp3" }, { "key": "original-emo_Triumph-de-0-seed1702-scale1.0", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "39634b66f705e930acb1e147e3cd7878d863165b92ac0ad56b841e64b52f0141", "task_id": "emo_Triumph-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.08998148888349533, "target_z": -0.19531250617335097, "ce": 5.967014789581299, "genuineness": 4.6203155517578125, "identity": 0.5294140577316284, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/9eb44b180f9f6c99962ba0f7.mp3" }, { "key": "original-emo_Triumph-de-1-seed1701-scale0.0", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "7aae8c9db65b1dc3ca9d884ce5066af391deeccc757c657768ad38c48272c623", "task_id": "emo_Triumph-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 1.9174124002456665, "target_z": 3.2656250264572186, "ce": 6.41180419921875, "genuineness": 4.055472373962402, "identity": 0.4462176561355591, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/cf0f78bfb17d1fd807f015e3.mp3" }, { "key": "original-emo_Triumph-de-1-seed1701-scale0.5", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "16e3c55bc58f21838f7f75259be0928801a36cd7e051d3fb47849c303d5d2a67", "task_id": "emo_Triumph-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 1.397646427154541, "target_z": 2.281249883588239, "ce": 6.372091293334961, "genuineness": 4.168440818786621, "identity": 0.5746313333511353, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/a3569ae6f15f32bf2c18468e.mp3" }, { "key": "original-emo_Triumph-de-1-seed1701-scale0.75", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "2402273c568dcf6d47bdba114b0c032f5f15f2e643e6a301ffa1fee27ef78d9b", "task_id": "emo_Triumph-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 1.1707645654678345, "target_z": 1.851562530866755, "ce": 6.419747352600098, "genuineness": 4.099404335021973, "identity": 0.5945010185241699, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/65dbd4c8190d26ff129173a1.mp3" }, { "key": "original-emo_Triumph-de-1-seed1701-scale1.0", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "4b09ab6f72831c6e1238857b04fca60b8e9f730734311082dc2afe6d009bded1", "task_id": "emo_Triumph-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.9562579989433289, "target_z": 1.4453125202838675, "ce": 6.395919322967529, "genuineness": 4.406930446624756, "identity": 0.6229323744773865, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/2a511c658cb92a19fae3d6b2.mp3" }, { "key": "original-emo_Triumph-de-1-seed1702-scale0.0", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "4978949c40e676d14bc9df9b264faca316d87f61ac85e1ddec621c9e37c26eac", "task_id": "emo_Triumph-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 1.3728957176208496, "target_z": 2.2343749735427814, "ce": 6.324435234069824, "genuineness": 4.2249250411987305, "identity": 0.5612653493881226, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/f614dddc9b0a68145942798c.mp3" }, { "key": "original-emo_Triumph-de-1-seed1702-scale0.5", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "d194010b9635e16bb2aa70cf462d58c8e4db3c3e29da66cce6af40d1d63f89e5", "task_id": "emo_Triumph-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 1.3398946523666382, "target_z": 2.1718748677139077, "ce": 6.2767791748046875, "genuineness": 4.193545341491699, "identity": 0.3946840763092041, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/06b67c6e682744148a306e66.mp3" }, { "key": "original-emo_Triumph-de-1-seed1702-scale0.75", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "5f3405a59513978864b6ce8f6c64ca1698927935213681d0a034b1f8d739dde6", "task_id": "emo_Triumph-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 1.3316444158554077, "target_z": 2.156249897698755, "ce": 6.332377910614014, "genuineness": 4.231201171875, "identity": 0.5838741660118103, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/319cb95bf316c93c5abdc2b5.mp3" }, { "key": "original-emo_Triumph-de-1-seed1702-scale1.0", "bucket": "emo_Triumph", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "1f8655b5dc68ce5b3a96434f65e3d1b90b6880f55494f86472f9c76332128c7b", "task_id": "emo_Triumph-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 1.2078906297683716, "target_z": 1.9218748959349408, "ce": 6.324435234069824, "genuineness": 4.369274139404297, "identity": 0.6118768453598022, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/de/dea181a22252f8eb83c4fe6f.mp3" }, { "key": "original-emo_Triumph-en-0-seed1701-scale0.0", "bucket": "emo_Triumph", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "b82f4c69f62ccb1007fb18dd1e7bc580527b01c81f9286a1ee3f12f42553e173", "task_id": "emo_Triumph-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.08946584910154343, "target_z": -0.196289066799298, "ce": 6.300607204437256, "genuineness": 4.093128204345703, "identity": 0.2114180028438568, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/18b4850f5674a28c0f9e0ff1.mp3" }, { "key": "original-emo_Triumph-en-0-seed1701-scale0.5", "bucket": "emo_Triumph", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "2ad5803bc7af58d881ba00be7e0eb1b822272c638c004c0ffea3444677cb0e6b", "task_id": "emo_Triumph-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.07090278714895248, "target_z": -0.231445305775457, "ce": 6.24500846862793, "genuineness": 3.9927117824554443, "identity": 0.2171618938446045, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/c4ec82da91b7dfade35ef62d.mp3" }, { "key": "original-emo_Triumph-en-0-seed1701-scale0.75", "bucket": "emo_Triumph", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "cecf06f2de60bd628d55c4f4dd35d363dc2a41b1fd6e64bbe1230a33a2f1cda6", "task_id": "emo_Triumph-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.09307533502578735, "target_z": -0.1894531283071523, "ce": 6.316492557525635, "genuineness": 4.080576419830322, "identity": 0.17790094017982483, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/e9184e7c3c5efb6a7c2c0d7f.mp3" }, { "key": "original-emo_Triumph-en-0-seed1701-scale1.0", "bucket": "emo_Triumph", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "f33c316913bc09d20beced863e449b9dafb65a8c9a1e74a284b9a99bd71cffc2", "task_id": "emo_Triumph-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.05388663709163666, "target_z": -0.2636718769842914, "ce": 6.284721851348877, "genuineness": 3.948779582977295, "identity": 0.4498078525066376, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/b8b7920d8aecfebc39963973.mp3" }, { "key": "original-emo_Triumph-en-0-seed1702-scale0.0", "bucket": "emo_Triumph", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "11179b3e5005b7f61b61347dc5d8ddda5efa4a9bc0dc644ebdc0c8376558061f", "task_id": "emo_Triumph-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.06987150013446808, "target_z": -0.23339844113786753, "ce": 6.316492557525635, "genuineness": 4.118232727050781, "identity": 0.23411908745765686, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/563eeadf9370fbbb980d9ef9.mp3" }, { "key": "original-emo_Triumph-en-0-seed1702-scale0.5", "bucket": "emo_Triumph", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "8c72fbe8cd0167a2a0debc896e949447f7c4cba6321485c988c9f4e363412827", "task_id": "emo_Triumph-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.11988865584135056, "target_z": -0.13867187698429137, "ce": 6.173524379730225, "genuineness": 3.9550557136535645, "identity": 0.1595660299062729, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/982645e99819b5fcabef1720.mp3" }, { "key": "original-emo_Triumph-en-0-seed1702-scale0.75", "bucket": "emo_Triumph", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "dbee5c0be0a92168141fdae1a1087297581632da3d1b064218a88b2ea6979641", "task_id": "emo_Triumph-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.08740328997373581, "target_z": -0.2001953093030861, "ce": 6.125868320465088, "genuineness": 4.036643981933594, "identity": 0.22221612930297852, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/8152f6e4c9c66d3d51d56f65.mp3" }, { "key": "original-emo_Triumph-en-0-seed1702-scale1.0", "bucket": "emo_Triumph", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "1a7efc2642d6b528b28e3e1cfc4b25fa36cfcf29856f28a5c43dc6040705eb0b", "task_id": "emo_Triumph-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.054917916655540466, "target_z": -0.26171875573239733, "ce": 6.062326908111572, "genuineness": 3.8295347690582275, "identity": 0.3298644721508026, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/2905c44e46298c5f207e9e6a.mp3" }, { "key": "original-emo_Triumph-en-1-seed1701-scale0.0", "bucket": "emo_Triumph", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "5085f8cb439086820a915ab608c98b6c7e6adf22405fde8c542b3f92e797607d", "task_id": "emo_Triumph-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.11060712486505508, "target_z": -0.15624999647237087, "ce": 6.324435234069824, "genuineness": 4.482243061065674, "identity": 0.6413633823394775, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/bc5829be1075a007bed48c99.mp3" }, { "key": "original-emo_Triumph-en-1-seed1701-scale0.5", "bucket": "emo_Triumph", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "eb7b5f2eb0c635946c18bc79d2bb73f56f18df41b421f80945151e9cc7a59e37", "task_id": "emo_Triumph-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.13510006666183472, "target_z": -0.10986326796627158, "ce": 6.41180419921875, "genuineness": 4.3504462242126465, "identity": 0.5472301840782166, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/6d573ef13270d25cb511252b.mp3" }, { "key": "original-emo_Triumph-en-1-seed1701-scale0.75", "bucket": "emo_Triumph", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "fc3ec130da359f7d18d57b1c4b47093a79db56bbb08ef43398bee033520cbbc1", "task_id": "emo_Triumph-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.0853407233953476, "target_z": -0.2041015659173907, "ce": 6.340320587158203, "genuineness": 4.306513786315918, "identity": 0.38604944944381714, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/889b326a74b3f015ae786903.mp3" }, { "key": "original-emo_Triumph-en-1-seed1701-scale1.0", "bucket": "emo_Triumph", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "75acc5e27c3a1c76abe800dc3524f6bbc4f04c1126ee608ac092a923328e53e4", "task_id": "emo_Triumph-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.06626202166080475, "target_z": -0.24023436551949673, "ce": 6.38797664642334, "genuineness": 4.6203155517578125, "identity": 0.3786773681640625, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/062251c8e1abe499df4c8418.mp3" }, { "key": "original-emo_Triumph-en-1-seed1702-scale0.0", "bucket": "emo_Triumph", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "b4dbb8caf57c667571f8b744f73c32d3e27a4422936db1e5e3adbc09e9f270e4", "task_id": "emo_Triumph-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.09307533502578735, "target_z": -0.1894531283071523, "ce": 6.2767791748046875, "genuineness": 4.20609712600708, "identity": 0.2828894257545471, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/60e81c4581b99cdbc7fbcdda.mp3" }, { "key": "original-emo_Triumph-en-1-seed1702-scale0.5", "bucket": "emo_Triumph", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "161b5b8a18aa4529a2cd7bd7be33440948d1de14add4751f5c7b2fe3b7c62f39", "task_id": "emo_Triumph-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.05182407796382904, "target_z": -0.26757811948807947, "ce": 6.252951145172119, "genuineness": 4.406930446624756, "identity": 0.4989219307899475, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/b0c52562d6e5a5a1857b0260.mp3" }, { "key": "original-emo_Triumph-en-1-seed1702-scale0.75", "bucket": "emo_Triumph", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "f513fbd4e229b10e0b01dc89ce750ba517da0471a4f848b6562532f0222677f4", "task_id": "emo_Triumph-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.0997786670923233, "target_z": -0.17675781194880794, "ce": 6.23706579208374, "genuineness": 4.162164688110352, "identity": 0.5434874296188354, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/251bc70fc8e7d8929b502d06.mp3" }, { "key": "original-emo_Triumph-en-1-seed1702-scale1.0", "bucket": "emo_Triumph", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "664d37d63f21562640ce17f0c799e2ebb6ab6fd558aef35e619846ff3ed84f6b", "task_id": "emo_Triumph-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.054917916655540466, "target_z": -0.26171875573239733, "ce": 6.24500846862793, "genuineness": 4.068024158477783, "identity": 0.32922840118408203, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/en/f6478d8cf1b8ae27fca7149c.mp3" }, { "key": "original-emo_Triumph-es-0-seed1701-scale0.0", "bucket": "emo_Triumph", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "f5821f026c8d39056f7bd2f4d0f60b44b7bf4e54f5e93b6dce0250163480e807", "task_id": "emo_Triumph-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.0992630273103714, "target_z": -0.17773437257475497, "ce": 6.078212261199951, "genuineness": 3.9927117824554443, "identity": 0.5928565263748169, "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_Triumph/es/fecf38413508cdba35e2f7fa.mp3" }, { "key": "original-emo_Triumph-es-0-seed1701-scale0.5", "bucket": "emo_Triumph", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "6c40a55e2be49ddf1daf2a242a0c69cae6ad7c5d6b1c209e6183b1fac78af88c", "task_id": "emo_Triumph-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.10287251323461533, "target_z": -0.1708984340826093, "ce": 6.165581703186035, "genuineness": 3.948779582977295, "identity": 0.5723187923431396, "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_Triumph/es/adcd8943d291de470e2c2934.mp3" }, { "key": "original-emo_Triumph-es-0-seed1701-scale0.75", "bucket": "emo_Triumph", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "3bb93bf110a56d4b5a5dede1998e5cef4c856ddd7b9d9f4851f2117e62fc7a13", "task_id": "emo_Triumph-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.04047997295856476, "target_z": -0.2890625097009801, "ce": 6.2767791748046875, "genuineness": 4.494794845581055, "identity": 0.5075832605361938, "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_Triumph/es/a2201083d63d202bea4a2278.mp3" }, { "key": "original-emo_Triumph-es-0-seed1701-scale1.0", "bucket": "emo_Triumph", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "1e3a6a06035392960bcdc9de001d04214aded2edc152fcdd6d91f67d79306fa0", "task_id": "emo_Triumph-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.027073323726654053, "target_z": -0.3144531141966358, "ce": 5.8875885009765625, "genuineness": 4.256305694580078, "identity": 0.6019648313522339, "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_Triumph/es/732a426edaf3a4387e1e3bc2.mp3" }, { "key": "original-emo_Triumph-es-0-seed1702-scale0.0", "bucket": "emo_Triumph", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "a9006363d77cd2317c01217e38c5bbafe75db414b07d9e5e041d6540ceb21fac", "task_id": "emo_Triumph-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.14360812306404114, "target_z": -0.09375001763814562, "ce": 6.157639026641846, "genuineness": 4.143336772918701, "identity": 0.5057502388954163, "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_Triumph/es/b6b5655b1759cd3777e68f0f.mp3" }, { "key": "original-emo_Triumph-es-0-seed1702-scale0.5", "bucket": "emo_Triumph", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "a1b9d652f8ad38806a91c3436d4df3f64d607557c1253d18d2eb02ad2c275685", "task_id": "emo_Triumph-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.03738613426685333, "target_z": -0.29492187345666226, "ce": 5.808161735534668, "genuineness": 4.049196243286133, "identity": 0.593636155128479, "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_Triumph/es/12b2e164bfe01ce24aed3f6a.mp3" }, { "key": "original-emo_Triumph-es-0-seed1702-scale0.75", "bucket": "emo_Triumph", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "3d0269899a02122db092374985ef61492e97bb800787c00405c07b5c7f6ff8ba", "task_id": "emo_Triumph-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.08173123747110367, "target_z": -0.2109375044095364, "ce": 5.974957466125488, "genuineness": 3.8295347690582275, "identity": 0.5017013549804688, "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_Triumph/es/c369b173c4beff5f9deef013.mp3" }, { "key": "original-emo_Triumph-es-0-seed1702-scale1.0", "bucket": "emo_Triumph", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "7c878f9d8ec286c51436e11c9891c7e198c77aaa11c76162dcd4d5c1ce685ae5", "task_id": "emo_Triumph-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.031198441982269287, "target_z": -0.3066406291890596, "ce": 5.764476776123047, "genuineness": 3.9048471450805664, "identity": 0.5265339612960815, "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_Triumph/es/6559874fa93241f83ecfc457.mp3" }, { "key": "original-emo_Triumph-es-1-seed1701-scale0.0", "bucket": "emo_Triumph", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "dd471a838b40336223ea4ff71f600b634cd63e63aea4da3d6f81a859b148dc17", "task_id": "emo_Triumph-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.02810460329055786, "target_z": -0.31249999294474173, "ce": 6.1020402908325195, "genuineness": 4.124508857727051, "identity": 0.576665997505188, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/es/6ec5b31a152fe31ad5ffb14e.mp3" }, { "key": "original-emo_Triumph-es-1-seed1701-scale0.5", "bucket": "emo_Triumph", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "e4ea9a322bb179a435c42d40466199a6d29d6cb763875af620f40fac4ee839c7", "task_id": "emo_Triumph-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.022948190569877625, "target_z": -0.322265627425245, "ce": 6.348263263702393, "genuineness": 4.607763767242432, "identity": 0.5169991254806519, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/es/c13b7f81cbf29c239748d98c.mp3" }, { "key": "original-emo_Triumph-es-1-seed1701-scale0.75", "bucket": "emo_Triumph", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "91c47b9c1ef1ce4144d4af0fade3ff869d79aa54d7d7cc71c1e3331ae9b0adde", "task_id": "emo_Triumph-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.151858389377594, "target_z": -0.07812499118092718, "ce": 6.205295085906982, "genuineness": 4.3127899169921875, "identity": 0.5801228284835815, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/es/181a8b554d28be0bef43c1e2.mp3" }, { "key": "original-emo_Triumph-es-1-seed1701-scale1.0", "bucket": "emo_Triumph", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "5b9b9d44c7ab751299a98dde58519ab3373f0b162834436679fa343ce2a5f513", "task_id": "emo_Triumph-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.13870954513549805, "target_z": -0.10302734358464238, "ce": 6.181467056274414, "genuineness": 4.356721878051758, "identity": 0.6905872821807861, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/es/14c0fb4e808716f76995b4a7.mp3" }, { "key": "original-emo_Triumph-es-1-seed1702-scale0.0", "bucket": "emo_Triumph", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "060b85e48aaea65446bf65724378a1ef0a31e8c0374cd7dc81d48412748d2526", "task_id": "emo_Triumph-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.0012912750244140625, "target_z": -0.3632812583781192, "ce": 6.221180438995361, "genuineness": 4.3504462242126465, "identity": 0.7510045766830444, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/es/78f946078180a5d30ddc6894.mp3" }, { "key": "original-emo_Triumph-es-1-seed1702-scale0.5", "bucket": "emo_Triumph", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "abd8a7fa6d9ceadaaa4554fed3cb8c1416cdd369a20aa79f24181f41794a79c8", "task_id": "emo_Triumph-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.054917916655540466, "target_z": -0.26171875573239733, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.6430222988128662, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/es/750f0c5583b9235d2c6f0257.mp3" }, { "key": "original-emo_Triumph-es-1-seed1702-scale0.75", "bucket": "emo_Triumph", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "78057b8c242dcaf5b62a5253be75e917935b054f9d2430201b095563a1d32998", "task_id": "emo_Triumph-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.09565354138612747, "target_z": -0.18457031106690067, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.5630357265472412, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/es/868bd30be90617c6d90ac6fc.mp3" }, { "key": "original-emo_Triumph-es-1-seed1702-scale1.0", "bucket": "emo_Triumph", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "0189369c7858e2ec029166d1c0ba143cc845de928498310709fe2d034a6f3899", "task_id": "emo_Triumph-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.09616918116807938, "target_z": -0.18359375044095363, "ce": 6.125868320465088, "genuineness": 4.457139015197754, "identity": 0.4239708185195923, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/es/3ac8df428f2d36d6c51c431c.mp3" }, { "key": "original-emo_Triumph-fr-0-seed1701-scale0.0", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "27b609b12824a625d411fe5e68114c3765814a90f267ecb9911143f4e1000753", "task_id": "emo_Triumph-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.02604202926158905, "target_z": -0.31640626366956287, "ce": 6.173524379730225, "genuineness": 4.595211505889893, "identity": 0.5021548867225647, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/232562c029f6beccf50d3ab4.mp3" }, { "key": "original-emo_Triumph-fr-0-seed1701-scale0.5", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "e3340d5f3dc17ee3fbb6f2e6abb254968f41575bf46ab19dae06439745616a20", "task_id": "emo_Triumph-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.032229721546173096, "target_z": -0.30468750793716554, "ce": 6.09409761428833, "genuineness": 4.406930446624756, "identity": 0.8229462504386902, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/2003c0fcc1b7e3d1cdbebc00.mp3" }, { "key": "original-emo_Triumph-fr-0-seed1701-scale0.75", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "5dc554a93cb079a586e95b0678aa49aa316f9277bfe8a3ec5269654e75a2da61", "task_id": "emo_Triumph-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.033261001110076904, "target_z": -0.3027343866852715, "ce": 6.23706579208374, "genuineness": 4.444586753845215, "identity": 0.7846059799194336, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/2a2122a6ed0d3a5699084067.mp3" }, { "key": "original-emo_Triumph-fr-0-seed1701-scale1.0", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "f338f33213fb28b122d93c513c8b9813994f08a779c45c015e6617ff45b89be6", "task_id": "emo_Triumph-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": -0.0069589763879776, "target_z": -0.3789062566143046, "ce": 6.24500846862793, "genuineness": 4.632867813110352, "identity": 0.6411200165748596, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/22f098570b2ec9ccb6b79182.mp3" }, { "key": "original-emo_Triumph-fr-0-seed1702-scale0.0", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "d3a01f599b098479be02a4896c67b6562bd7a21dacb777512cb1472adcca34ea", "task_id": "emo_Triumph-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.1920139044523239, "target_z": -0.002075205440653933, "ce": 6.197352409362793, "genuineness": 3.9927117824554443, "identity": 0.7815524935722351, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/9275bb84b1522771ab6bc077.mp3" }, { "key": "original-emo_Triumph-fr-0-seed1702-scale0.5", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "b01c54ae46b87f4ee39c2f702ce25e62c03882eb7b0ced200264526584f610e6", "task_id": "emo_Triumph-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.03944869339466095, "target_z": -0.29101563095287414, "ce": 6.181467056274414, "genuineness": 4.419482707977295, "identity": 0.5999194979667664, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/de38980883d543ffed86ae64.mp3" }, { "key": "original-emo_Triumph-fr-0-seed1702-scale0.75", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "7c75de33ad80cbc52b1b28f3a67b82e71f6953ba2552f3ed5f739cbb45f838e3", "task_id": "emo_Triumph-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.020885631442070007, "target_z": -0.32617186992903313, "ce": 6.24500846862793, "genuineness": 4.268857479095459, "identity": 0.6813067197799683, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/e0169f7432fa3f95cb1e2ab1.mp3" }, { "key": "original-emo_Triumph-fr-0-seed1702-scale1.0", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "19db107a1ca5907f2ad1a6ebd1766dee8e59f4459d6bb45c5f627b7ac51b0a4e", "task_id": "emo_Triumph-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.10080994665622711, "target_z": -0.1748046906969139, "ce": 6.24500846862793, "genuineness": 4.419482707977295, "identity": 0.608070969581604, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/f418aba52a7e54ea1b0e634b.mp3" }, { "key": "original-emo_Triumph-fr-1-seed1701-scale0.0", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "89a000eb65e2f9bb8e0a39dfd9836ab1f733d7397b4145bad0f5046088ea9ed2", "task_id": "emo_Triumph-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.014697939157485962, "target_z": -0.33789062566143047, "ce": 6.1894097328186035, "genuineness": 4.469690799713135, "identity": 0.7951803207397461, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/ec6d7df0266c0fd96d040d97.mp3" }, { "key": "original-emo_Triumph-fr-1-seed1701-scale0.5", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "153253d8465cc5f4baa6521dfcf66dde89352d6f709b93007a91eefd9ba0f76a", "task_id": "emo_Triumph-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.17667359113693237, "target_z": -0.031127940504643997, "ce": 6.117925643920898, "genuineness": 4.3881025314331055, "identity": 0.7042486667633057, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/625f526a950c0f3e47f8f54f.mp3" }, { "key": "original-emo_Triumph-fr-1-seed1701-scale0.75", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "83c78addb803c8a3fc877d81d89a7d269b2b36412942a087f41fbea70bcf0f92", "task_id": "emo_Triumph-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.059043049812316895, "target_z": -0.2539062425037881, "ce": 6.23706579208374, "genuineness": 4.557555198669434, "identity": 0.7864029407501221, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/1d750d8508fce4a12174ef37.mp3" }, { "key": "original-emo_Triumph-fr-1-seed1701-scale1.0", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "4e6217c53e2c32aab083310f113eeb2b393ff5629c3d932e53746331342f3d54", "task_id": "emo_Triumph-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.3519269824028015, "target_z": 0.30078120899131144, "ce": 6.348263263702393, "genuineness": 4.425758361816406, "identity": 0.7297322750091553, "hypothesis": "J'ai trouvé la 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_Triumph/fr/4e0ec62e9672a54678f63f15.mp3" }, { "key": "original-emo_Triumph-fr-1-seed1702-scale0.0", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "a1c2f8a8f71b78b9c8dd7693f73f98c2881dc4675dfcc6203da6d7dcbbbde004", "task_id": "emo_Triumph-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.01882307231426239, "target_z": -0.33007811243282126, "ce": 6.332377910614014, "genuineness": 4.632867813110352, "identity": 0.8094609379768372, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/57ebbe64af99506558f48a50.mp3" }, { "key": "original-emo_Triumph-fr-1-seed1702-scale0.5", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "487f89954c8e56d304637072d78964e1185d47d746c81cff9e85ba33c1cebf68", "task_id": "emo_Triumph-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.03429229557514191, "target_z": -0.3007812372123444, "ce": 6.086154937744141, "genuineness": 4.8588056564331055, "identity": 0.7548710107803345, "hypothesis": "J'ai trouvé la petite boîte elle était près de 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_Triumph/fr/f3f4573f897f1c0fa4c24473.mp3" }, { "key": "original-emo_Triumph-fr-1-seed1702-scale0.75", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "f2ee66ec4a609ac22de7060bf8adf40ce392113e2b374503b25a6e79fb4a0e6e", "task_id": "emo_Triumph-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.07863739877939224, "target_z": -0.21679686816521856, "ce": 6.356205940246582, "genuineness": 4.645420074462891, "identity": 0.7876712083816528, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/5e6c8d0e44e898f4b5086909.mp3" }, { "key": "original-emo_Triumph-fr-1-seed1702-scale1.0", "bucket": "emo_Triumph", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "5a4a9c83a82405eabe1aad3a021d5f109f4226824dfcce4c7af8e2ca75a96c8d", "task_id": "emo_Triumph-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.1126696839928627, "target_z": -0.15234375396858277, "ce": 6.157639026641846, "genuineness": 4.3881025314331055, "identity": 0.7113171219825745, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/fr/da17fb9e12be147ea9204fff.mp3" }, { "key": "original-emo_Triumph-nl-0-seed1701-scale0.0", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "ba07826a85860d96a590f65ce5d455d4a20c038453259e43783b3bfe9c62d07e", "task_id": "emo_Triumph-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.08791892975568771, "target_z": -0.19921874867713907, "ce": 6.1020402908325195, "genuineness": 4.331617832183838, "identity": 0.7069319486618042, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/fc92d9ba95cc4270fc9e56aa.mp3" }, { "key": "original-emo_Triumph-nl-0-seed1701-scale0.5", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "ecac60a255a0e96972e2038278f71648c531ce02837ce79cf4e91d5f84e63b7b", "task_id": "emo_Triumph-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.07966867834329605, "target_z": -0.21484374691332453, "ce": 6.141753673553467, "genuineness": 4.268857479095459, "identity": 0.7283512353897095, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/f3aa8200f2e8eba50ea5d5d1.mp3" }, { "key": "original-emo_Triumph-nl-0-seed1701-scale0.75", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "82fa881761d0cdeee93bee6f8adba4f6ca1352cb2eb503f7e8897ba17fbb00f1", "task_id": "emo_Triumph-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.13381095230579376, "target_z": -0.11230469775217214, "ce": 6.205295085906982, "genuineness": 4.444586753845215, "identity": 0.6886287927627563, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/e09d6fef9002f88a50081b01.mp3" }, { "key": "original-emo_Triumph-nl-0-seed1701-scale1.0", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "42b94485d2ca957d017d04c698a7a9836f059e815b9476bf82138ef79dc0dd7f", "task_id": "emo_Triumph-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.14128774404525757, "target_z": -0.09814454045490725, "ce": 6.181467056274414, "genuineness": 4.331617832183838, "identity": 0.7148275971412659, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/d41918b6690a8c88793bf500.mp3" }, { "key": "original-emo_Triumph-nl-0-seed1702-scale0.0", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "1dd669510f89816d7ec578ff12e2559febded633b7a10c776acfb5cca3f45d83", "task_id": "emo_Triumph-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.0992630273103714, "target_z": -0.17773437257475497, "ce": 6.125868320465088, "genuineness": 4.406930446624756, "identity": 0.5447152256965637, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/fc3fcf5a631fa2188870f34f.mp3" }, { "key": "original-emo_Triumph-nl-0-seed1702-scale0.5", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "553b429773edec2b3162955f9deafb8c4ec22de28d73f987cf96b27f8f1fb8b8", "task_id": "emo_Triumph-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.05285535752773285, "target_z": -0.26562499823618546, "ce": 5.967014789581299, "genuineness": 4.15588903427124, "identity": 0.37551411986351013, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/1aad3f09ae4739b019d6b94d.mp3" }, { "key": "original-emo_Triumph-nl-0-seed1702-scale0.75", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "1e3cbbf911c40f0f0f26d5c05c9c7743fd488b8992b9d765efe4e471df08657a", "task_id": "emo_Triumph-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.04976151883602142, "target_z": -0.2714843619918676, "ce": 6.109982967376709, "genuineness": 4.243753433227539, "identity": 0.6335870623588562, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/ed8b5d39e466113115385474.mp3" }, { "key": "original-emo_Triumph-nl-0-seed1702-scale1.0", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "cf0b5239d39a39f9f6ced6d6d5ebc6b429e8a0bfa29b514087839327929fc975", "task_id": "emo_Triumph-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.07915303856134415, "target_z": -0.21582030753927153, "ce": 6.0146708488464355, "genuineness": 4.036643981933594, "identity": 0.7130864858627319, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/5ff8c1c420c8c179aa1954fc.mp3" }, { "key": "original-emo_Triumph-nl-1-seed1701-scale0.0", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "458334f3e1240a55d1fac101b8e1bf97a391931bdaf59bfccc539476521d2cbb", "task_id": "emo_Triumph-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.16565176844596863, "target_z": -0.052001966215811206, "ce": 6.221180438995361, "genuineness": 4.356721878051758, "identity": 0.531644344329834, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/3fe0e65c079bc991c4d7911a.mp3" }, { "key": "original-emo_Triumph-nl-1-seed1701-scale0.5", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "525d4814872ac0f45efccea11b9404af67e57809175669830a3324806323167f", "task_id": "emo_Triumph-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.12040429562330246, "target_z": -0.13769531635834437, "ce": 6.292664527893066, "genuineness": 4.319066047668457, "identity": 0.6832798719406128, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/90fc911201fcd0d191af572e.mp3" }, { "key": "original-emo_Triumph-nl-1-seed1701-scale0.75", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "06eef319f6f2562e4eabe04bb683fbbbc6dff7eef43021080e0bdfee66715f8a", "task_id": "emo_Triumph-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.08791892975568771, "target_z": -0.19921874867713907, "ce": 6.197352409362793, "genuineness": 4.344170093536377, "identity": 0.6484119296073914, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het Oude Raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/aee83dcbe4a7737a3b3b8349.mp3" }, { "key": "original-emo_Triumph-nl-1-seed1701-scale1.0", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "c89a3971a29bbf121e0586d80bf5c1fb95d11e62d48d1514d0e87ef2a3e31ad2", "task_id": "emo_Triumph-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.09152841567993164, "target_z": -0.1923828101849934, "ce": 6.117925643920898, "genuineness": 4.419482707977295, "identity": 0.5168287754058838, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/635163122785101c6a4c682b.mp3" }, { "key": "original-emo_Triumph-nl-1-seed1702-scale0.0", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "c3e829dc1dbd7dd9164c2adc9318fc78043ad5178d525c1d48a67a4a53e40312", "task_id": "emo_Triumph-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.08224687725305557, "target_z": -0.20996094378358937, "ce": 6.173524379730225, "genuineness": 4.469690799713135, "identity": 0.6526602506637573, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/9a874bca912f5660bff9a086.mp3" }, { "key": "original-emo_Triumph-nl-1-seed1702-scale0.5", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "fd383e8d68ba7da0be915126152969c4ae9199ffac5e50c32c0c784661a4f5aa", "task_id": "emo_Triumph-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.0987473875284195, "target_z": -0.178710933200702, "ce": 6.133810997009277, "genuineness": 4.344170093536377, "identity": 0.7810748219490051, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/8f545c6042c340119173417a.mp3" }, { "key": "original-emo_Triumph-nl-1-seed1702-scale0.75", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "f6b3b3d818a6ee497e7b2662c76e6e7070b3e08abaffcc74b2a4bd39e243ee2c", "task_id": "emo_Triumph-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.08224687725305557, "target_z": -0.20996094378358937, "ce": 6.23706579208374, "genuineness": 4.218649387359619, "identity": 0.7711522579193115, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/d1d28a97d1a376b4ccc304b4.mp3" }, { "key": "original-emo_Triumph-nl-1-seed1702-scale1.0", "bucket": "emo_Triumph", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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 Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "6d97d7da97ed07de2fe5a9a9c4c0e98e0d34658b89bae4b2ce1bcf984ed812d5", "mp3_sha256": "36004cdaf66a4e72abf2ec4cf53db71782f92aad25abba4b997dcf711a551ab2", "task_id": "emo_Triumph-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Triumph. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Triumph. 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 Triumph. 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 Triumph. 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": 0.0858563631772995, "target_z": -0.2031250052914437, "ce": 6.197352409362793, "genuineness": 4.457139015197754, "identity": 0.3814574182033539, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Triumph/nl/59fa29c0d22fce6526ab5562.mp3" } ], "source_standard_audio_unchanged": true }