{ "complete": true, "report": { "bucket": "vn_VOLT_reg_high", "label": "Emotionally volatile delivery with rapid or abrupt changes", "definition": { "id": "vn_VOLT_reg_high", "category": "bipolar", "head": "vn_VOLT_reg", "pole": "high", "label": "Emotionally volatile delivery with rapid or abrupt changes", "floor": 4.0, "canonical_dimension_name": "Volatility" }, "recipe_status": "new_canonical_dimension_extension", "manual_provenance": [], "selected_wording": { "id": "canonical-extension-P01", "general": "Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.", "inline": [ "Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.", "Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.", "Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear." ], "recipe": "P01", "cfg": 1.0, "timing_syntax": "canonical", "canonical_labels": true, "lexical_proxy": false, "origin": "new_canonical_manual_extension_requires_new_evidence" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.6458496322001069, "target_raw": 2.1235142648220062, "ce": 6.10144464969635, "genuineness": 4.097207868099213, "identity": 0.5402026057243348, "wer": 0.04751461988304093, "valid_fraction": 0.95, "identity_delta": -0.03674885928630829, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 0.05664062073725795, "target_raw": 2.7335966885089875, "ce": 5.873489952087402, "genuineness": 3.880684494972229, "identity": 0.580115333199501, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.0031638681888580323, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.6458496322001069, "target_raw": 2.1235142648220062, "ce": 6.10144464969635, "genuineness": 4.097207868099213, "identity": 0.5402026057243348, "wer": 0.04751461988304093, "valid_fraction": 0.95, "identity_delta": -0.03674885928630829, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": -0.8142578042560178, "target_raw": 1.9772590458393098, "ce": 6.046640110015869, "genuineness": 4.111328995227813, "identity": 0.5284538760781288, "wer": 0.015694444444444445, "valid_fraction": 1, "identity_delta": -0.04849758893251419, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": -1.0750976490717032, "target_raw": 1.7507309138774871, "ce": 6.101047468185425, "genuineness": 4.1624786972999575, "identity": 0.5484208598732948, "wer": 0.022602339181286547, "valid_fraction": 0.95, "identity_delta": -0.028530605137348175, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -1.222851547124638, "target_raw": 1.6224130392074585, "ce": 6.204897952079773, "genuineness": 4.35860493183136, "identity": 0.5381301671266556, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03882129788398743, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 0.3065429802446582, "target_raw": 2.950626087188721, "ce": 5.772220921516419, "genuineness": 3.8433420777320864, "identity": 0.4400887433439493, "wer": 0.062099458204334365, "valid_fraction": 0.9, "identity_delta": -0.1368627216666937, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": -0.26372070776642903, "target_raw": 2.455376720428467, "ce": 5.880836915969849, "genuineness": 3.9045334458351135, "identity": 0.47923841923475263, "wer": 0.018059640522875817, "valid_fraction": 0.95, "identity_delta": -0.09771304577589035, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -1.0791259842719638, "target_raw": 1.7472324788570404, "ce": 6.163596034049988, "genuineness": 4.277330303192139, "identity": 0.524262585490942, "wer": 0.014705882352941176, "valid_fraction": 0.95, "identity_delta": -0.052688879519701005, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -1.2126952887063926, "target_raw": 1.631233310699463, "ce": 6.1461221933364865, "genuineness": 4.244381082057953, "identity": 0.5228141874074936, "wer": 0.06215686274509804, "valid_fraction": 0.9, "identity_delta": -0.05413727760314942, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 0.05664062073725795, "target_raw": 2.7335966885089875, "ce": 5.873489952087402, "genuineness": 3.880684494972229, "identity": 0.580115333199501, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.0031638681888580323, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": -0.49799806963308274, "target_raw": 2.2519169569015505, "ce": 6.039293217658996, "genuineness": 4.091873264312744, "identity": 0.5611090570688247, "wer": 0.012732843137254903, "valid_fraction": 1, "identity_delta": -0.015842407941818237, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": -0.5993164376240495, "target_raw": 2.1639263331890106, "ce": 6.066496849060059, "genuineness": 4.060493040084839, "identity": 0.5484283521771431, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": -0.028523112833499908, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": -0.6539550799514107, "target_raw": 2.1164750337600706, "ce": 6.04147744178772, "genuineness": 4.054530823230744, "identity": 0.5529352739453316, "wer": 0.009791666666666667, "valid_fraction": 1, "identity_delta": -0.024016191065311433, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": -0.7500976885355793, "target_raw": 2.0329793334007262, "ce": 6.041675996780396, "genuineness": 4.087793838977814, "identity": 0.5500271394848824, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.02692432552576065, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": -0.760449234802307, "target_raw": 2.023989462852478, "ce": 6.0543842792510985, "genuineness": 4.111172068119049, "identity": 0.558670212328434, "wer": 0.0061111111111111106, "valid_fraction": 1, "identity_delta": -0.018281252682209016, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.9552734273525292, "target_raw": 1.8547930717468262, "ce": 6.117330002784729, "genuineness": 4.235280764102936, "identity": 0.5386378452181816, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.038313619792461395, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": -0.9614257632673948, "target_raw": 1.849450033903122, "ce": 6.074439549446106, "genuineness": 4.14114019870758, "identity": 0.586686585843563, "wer": 0.01415204678362573, "valid_fraction": 1, "identity_delta": 0.009735120832920075, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": -0.9652343704691609, "target_raw": 1.8461424231529235, "ce": 6.121499848365784, "genuineness": 4.165930509567261, "identity": 0.530050353705883, "wer": 0.009089912280701754, "valid_fraction": 1, "identity_delta": -0.046901111304759976, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -1.049853506660507, "target_raw": 1.7726543605327607, "ce": 6.159029030799866, "genuineness": 4.268543779850006, "identity": 0.5575332790613174, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.01941818594932556, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -1.0897460907942307, "target_raw": 1.738009375333786, "ce": 6.098466110229492, "genuineness": 4.189779472351074, "identity": 0.5674783989787102, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.00947306603193283, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -1.1443359489075267, "target_raw": 1.6906004428863526, "ce": 6.191395378112793, "genuineness": 4.237163603305817, "identity": 0.571339850127697, "wer": 0.01067251461988304, "valid_fraction": 0.95, "identity_delta": -0.005611614882946014, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -1.1937500132976104, "target_raw": 1.6476864635944366, "ce": 6.169950175285339, "genuineness": 4.332559430599213, "identity": 0.5746109038591385, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": -0.0023405611515045165, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -1.1998046778351037, "target_raw": 1.6424282491207123, "ce": 6.1395694494247435, "genuineness": 4.147259330749511, "identity": 0.5666145503520965, "wer": 0.006666666666666666, "valid_fraction": 1, "identity_delta": -0.010336914658546447, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -1.2062499867023897, "target_raw": 1.6368307769298553, "ce": 6.179084277153015, "genuineness": 4.284233891963959, "identity": 0.5516957908868789, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.02525567412376404, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -1.304589834091806, "target_raw": 1.5514268696308136, "ce": 6.178091430664063, "genuineness": 4.242812085151672, "identity": 0.592466090619564, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.015514625608921051, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 0.5126465113556102, "target_raw": 3.1296180963516234, "ce": 5.608502578735352, "genuineness": 3.775717723369598, "identity": 0.4618894584476948, "wer": 0.026036936704506363, "valid_fraction": 0.95, "identity_delta": -0.11506200656294822, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 0.37680664766589705, "target_raw": 3.011647045612335, "ce": 5.775497245788574, "genuineness": 3.7903095364570616, "identity": 0.5036630377173423, "wer": 0.012569444444444444, "valid_fraction": 1, "identity_delta": -0.07328842729330062, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 0.19516601148625282, "target_raw": 2.8539000034332274, "ce": 5.762093997001648, "genuineness": 3.8278088688850405, "identity": 0.4679836809635162, "wer": 0.03610745614035087, "valid_fraction": 0.95, "identity_delta": -0.10896778404712677, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 0.12216797102212194, "target_raw": 2.7905043601989745, "ce": 5.835166597366333, "genuineness": 3.902336823940277, "identity": 0.5232969790697097, "wer": 0.02031798245614035, "valid_fraction": 0.95, "identity_delta": -0.05365448594093323, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 0.022265601219797527, "target_raw": 2.7037434697151186, "ce": 5.9114161968231205, "genuineness": 3.962900626659393, "identity": 0.4747575126588345, "wer": 0.022911936704506364, "valid_fraction": 0.95, "identity_delta": -0.10219395235180855, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": -0.17377925362760527, "target_raw": 2.5334869861602782, "ce": 5.931272888183594, "genuineness": 4.01499172449112, "identity": 0.49350671023130416, "wer": 0.009583333333333333, "valid_fraction": 1, "identity_delta": -0.08344475477933884, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": -0.4395507514711275, "target_raw": 2.302675926685333, "ce": 6.017649412155151, "genuineness": 4.013422739505768, "identity": 0.50231132209301, "wer": 0.009791666666666667, "valid_fraction": 1, "identity_delta": -0.07464014291763306, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -1.2597656312466596, "target_raw": 1.5903547525405883, "ce": 6.17551007270813, "genuineness": 4.29804117679596, "identity": 0.5246416293084621, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.05230983570218086, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -1.3607421871648788, "target_raw": 1.5026609778404236, "ce": 6.198940944671631, "genuineness": 4.356722140312195, "identity": 0.576951465010643, "wer": 0.005555555555555555, "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": -1.3537109392560354, "target_raw": 1.5087673127651215, "ce": 6.190601134300232, "genuineness": 4.316241693496704, "identity": 0.5961843632161618, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.019232898205518722, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -1.2203124825200766, "target_raw": 1.6246181070804595, "ce": 6.138576579093933, "genuineness": 4.288313317298889, "identity": 0.5838449254631997, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.00689346045255661, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -1.3892578231300454, "target_raw": 1.4778963804244996, "ce": 6.153270554542542, "genuineness": 4.32000732421875, "identity": 0.5661222621798515, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.010829202830791473, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -1.228749995109911, "target_raw": 1.6172904920578004, "ce": 6.227852258682251, "genuineness": 4.338521647453308, "identity": 0.5755038475990295, "wer": 0.0028138528138528136, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": -0.6421484189021123, "target_raw": 2.126728608608246, "ce": 6.166614246368408, "genuineness": 4.1675622940063475, "identity": 0.5294986745715141, "wer": 0.022006399397703744, "valid_fraction": 0.96, "identity_delta": -0.04600517302751541, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": -0.2700488054902419, "target_raw": 2.449881041049957, "ce": 6.031350545883178, "genuineness": 3.9640930843353273, "identity": 0.5147908115386963, "wer": 0.015333333333333332, "valid_fraction": 1, "identity_delta": -0.06071303606033325, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": -0.3799218779973243, "target_raw": 2.3544610261917116, "ce": 6.086949224472046, "genuineness": 4.0348867988586425, "identity": 0.5584957027435302, "wer": 0.011714191605495953, "valid_fraction": 1, "identity_delta": -0.017008144855499268, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.10987307250708239, "ci95_z": [ 0.028925807707150853, 0.2063769670425847 ], "language_deltas": { "en": 0.06923832042567175, "de": -0.015624963324332603, "fr": 0.053320322379373855, "nl": 0.14702146910352556, "es": 0.2954102139511734 }, "languages_improved": 4, "clear_gain": true, "delta_ce": -0.05559867858886719, "delta_genuineness": -0.07079371452331543, "delta_wer": 0.00361914172783738, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "adapter_vs_best_manual": { "n": 50, "delta_z": 0.3720996134118703, "ci95_z": [ 0.30787109958781184, 0.43632812723592884 ], "language_deltas": { "en": 0.3042968885925171, "de": 0.30429687486595147, "fr": 0.32216797102212197, "nl": 0.4727050331952967, "es": 0.45703129938346443 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.13526370048522948, "delta_genuineness": -0.2034692096710205, "delta_wer": -0.006673066064370412, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.5866015762077987, "ci95_z": [ 0.45462891705564895, 0.7398633122326279 ], "language_deltas": { "en": 0.656152373662921, "de": 0.41289063146113736, "fr": 0.8654297200871883, "nl": 0.44882816652822277, "es": 0.5497069892995244 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.06123801231384277, "delta_genuineness": -0.17095935344696045, "delta_wer": 0.01919254658385093, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 3.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793035256.019068, "example": { "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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.", "language": "de", "seed": 1701, "scale": 0.0, "cfg": 3.0, "frames": 128, "reference": true } }, "rows": [ { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "00142a98d1d5001d043c4fc80dad06405dc692746a2d9521ca6f3cb0d23bea52", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7a20b34794628fbd4a40020dc759eaafae37d28e1d75b4a6d7402ea265a7be61", "generation_seconds_batch": 14.673926985939033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.064356565475464, "target_z": 0.4374999613940343, "ce": 5.935244083404541, "genuineness": 3.71028995513916, "identity": 0.5145523548126221, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/00142a98d1d5001d043c4fc80dad06405dc692746a2d9521ca6f3cb0d23bea52.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": "00bfa3d3ce39e9c9a6ff86d98cc6f627dcefe51fd937f712b5e139df7611f8a2", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "b28ce75afa2fbec9ab8955aa678e7ecf46b2bfacb8b18b80cfb8dfede8b99faa", "generation_seconds_batch": 15.164854426984675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8396968841552734, "target_z": -0.9726562009382519, "ce": 6.308549880981445, "genuineness": 4.093128204345703, "identity": 0.40158379077911377, "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/vn_VOLT_reg_high/00bfa3d3ce39e9c9a6ff86d98cc6f627dcefe51fd937f712b5e139df7611f8a2.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "019a1de121d7731dfc93ab375d2ee47875f5b0dace2f2243045e880342c76deb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c704b78d56b60f8ab8dc700a6136f9be176e19a657167a738f157578e68c10a", "generation_seconds_batch": 15.712374120019376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.58526611328125, "target_z": -1.2656250353888019, "ce": 6.419747352600098, "genuineness": 4.482243061065674, "identity": 0.5104590058326721, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/019a1de121d7731dfc93ab375d2ee47875f5b0dace2f2243045e880342c76deb.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "01c253d6da3015bad6cbd79da21fb70615e53149c659d3fd9d61b19ab1807aef", "generation_seconds_batch": 16.136823267908767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.374936819076538, "target_z": -1.5078124404824695, "ce": 5.95112943649292, "genuineness": 4.105680465698242, "identity": 0.6941602230072021, "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/vn_VOLT_reg_high/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.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": "02a1794e56792c09e4d62ab44f0d9408b06c183e055f65cbd05629f2cc1af1f5", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "526b2d7df000469131b800f42181468aeb86b120da10d691a1fec7f0c1725489", "generation_seconds_batch": 13.748697534902021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7522549629211426, "target_z": 0.07812502252014665, "ce": 5.708878040313721, "genuineness": 3.7667744159698486, "identity": 0.4584713876247406, "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/vn_VOLT_reg_high/02a1794e56792c09e4d62ab44f0d9408b06c183e055f65cbd05629f2cc1af1f5.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "02a2761383726322c9a0cb611c93c24fd437b12175c506580011d90d3c231694", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2f22e087a16b461a9790a2ee555c86eee11c5f67db1d4c10c8e10de071b56ea0", "generation_seconds_batch": 14.981461432995275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.368912696838379, "target_z": -0.3632812449061573, "ce": 5.387199878692627, "genuineness": 3.613011360168457, "identity": 0.4045759439468384, "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/vn_VOLT_reg_high/02a2761383726322c9a0cb611c93c24fd437b12175c506580011d90d3c231694.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "02bfefb9d521cb6d8f752b6172524d168bc722565e9aea3b6928099caf46767e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "25a89ead190f2cd7533d3cd3413611d7602e1b2e1924039bd742f60b016ef56a", "generation_seconds_batch": 15.08631440391764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8193423748016357, "target_z": -0.9960937626005583, "ce": 6.340320587158203, "genuineness": 4.3504462242126465, "identity": 0.41611358523368835, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/02bfefb9d521cb6d8f752b6172524d168bc722565e9aea3b6928099caf46767e.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "037b8c9ba22a203f98d3a8269017db5b50733fe3b989fa88fa25ef3ec607b86a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7cacc76b39c063799444f801db8c11f47e84c8537171abe61d70af5009d9d26c", "generation_seconds_batch": 15.629513395950198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8099257946014404, "target_z": 0.14453112694348436, "ce": 5.871703147888184, "genuineness": 3.7291181087493896, "identity": 0.6185420155525208, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/037b8c9ba22a203f98d3a8269017db5b50733fe3b989fa88fa25ef3ec607b86a.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "03ae5864805331283d7f651cd9b84cd625bf41a2465810d8d7f554d3a0392dcc", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b579ecebcf5700ae1c0513953f3ea625cd59ade79b23942ad7a7bf4643c82c1", "generation_seconds_batch": 15.118541868054308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.53344464302063, "target_z": -0.17382801038853937, "ce": 5.657250881195068, "genuineness": 3.9676074981689453, "identity": 0.67791748046875, "hypothesis": "La porte Il est encore ouverte J'ai posé ton manteau sur la chaise Dis-moi quand tu es prêt", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/03ae5864805331283d7f651cd9b84cd625bf41a2465810d8d7f554d3a0392dcc.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "03ebb60e04ba0fd5a1073271eadd1376c2b98a79fa66ec396e9726b99c40aed4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "de594c2e07ff9b823377c09abc82f4bc86ac2df24c3b85440ab4b35d8e66b1c9", "generation_seconds_batch": 20.198364231036976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.951646327972412, "target_z": -0.8437500235925346, "ce": 6.062326908111572, "genuineness": 3.6789097785949707, "identity": 0.33422940969467163, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/03ebb60e04ba0fd5a1073271eadd1376c2b98a79fa66ec396e9726b99c40aed4.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "0410a1b9275c77685b29e874f08308efff49d4159025ed677dfb734f755f456a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7a2e3d8ec7e0cb23bf0b00f0fe5abc1a67de8b0f34f8cefef8cc93f01aee1e7b", "generation_seconds_batch": 15.105598498950712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.58526611328125, "target_z": -1.2656250353888019, "ce": 6.213237762451172, "genuineness": 4.193545341491699, "identity": 0.6168984770774841, "hypothesis": "I've tried the petite boat. It was pretty fenêtre. We've got what?", "wer": 0.8947368421052632, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0410a1b9275c77685b29e874f08308efff49d4159025ed677dfb734f755f456a.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": "0450f5fed9f64cad622ead055718c1adc25b7c9ee5351c9a76813971986352e2", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "ec8f3bc2668ba6a75ce8c425dd432ca77deffb2ccd31244a3f75d2fe378241d5", "generation_seconds_batch": 15.854356413008645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5198748111724854, "target_z": -0.18945323451761795, "ce": 6.086154937744141, "genuineness": 4.061748504638672, "identity": 0.5785341262817383, "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/vn_VOLT_reg_high/0450f5fed9f64cad622ead055718c1adc25b7c9ee5351c9a76813971986352e2.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "0452ac10e7e54d6d1c32a7bc5ad54e7324a1ed0d148d8b651c16075e8a5ef1d0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "48567326ebf62da15bda0a81d022bc3f0a2244cc5c7ce2e1b4422d4132d2cec0", "generation_seconds_batch": 17.359654592932202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5174179077148438, "target_z": -1.3437500579089485, "ce": 6.324435234069824, "genuineness": 4.381826400756836, "identity": 0.4195893108844757, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0452ac10e7e54d6d1c32a7bc5ad54e7324a1ed0d148d8b651c16075e8a5ef1d0.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "04d6adb5de5a4d82a8c1c5596caada092470be91ee68204389108e24a8672c39", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "44c60e63cb8b1dd41e5b950dc2a65f3f23b513d16d57c82c44fde13fd393380a", "generation_seconds_batch": 22.10424585500732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9923553466796875, "target_z": -0.796874900267922, "ce": 6.070269584655762, "genuineness": 4.250029563903809, "identity": 0.4988255202770233, "hypothesis": "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/vn_VOLT_reg_high/04d6adb5de5a4d82a8c1c5596caada092470be91ee68204389108e24a8672c39.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": "04dd908a08780af88579c565535e4ecaad3897475f5a33931648574e6a933c96", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e61f31bdc61e9ad27c9735b6796f15c0f4c507cc86ad0fa298c248823a67f7c2", "generation_seconds_batch": 13.61783776897937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0873427391052246, "target_z": -0.6874999785522413, "ce": 5.9431867599487305, "genuineness": 3.9299514293670654, "identity": 0.7232068181037903, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/04dd908a08780af88579c565535e4ecaad3897475f5a33931648574e6a933c96.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "05096e631cf8dc91eb00a69f26d09e728db8bb32d0163e2e459eaeb2c553fe36", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "57e81952198ce9529551e668cc984b4b0817b04a2470dcaedb1ec5900dd3dda2", "generation_seconds_batch": 21.59177334595006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4248874187469482, "target_z": -0.2988281562332986, "ce": 6.078212261199951, "genuineness": 4.18099308013916, "identity": 0.457516074180603, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/05096e631cf8dc91eb00a69f26d09e728db8bb32d0163e2e459eaeb2c553fe36.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "0589b78de7586acd9df0cabcafc3b0c734413dd40ce9bab76462428bf6ba3db0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "888b6e8756c5c753b469bf878127c97dd38f97d29dc5f04af24416e1b904f8d8", "generation_seconds_batch": 20.998227727948688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.250939130783081, "target_z": 0.6523437733244376, "ce": 5.895530700683594, "genuineness": 3.6663577556610107, "identity": 0.5684018731117249, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0589b78de7586acd9df0cabcafc3b0c734413dd40ce9bab76462428bf6ba3db0.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "d9566ee6c7cf3b382484d224fec2e417fbb6db56f87be3ee9c26ccc908980124", "generation_seconds_batch": 13.503507282934152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.734532117843628, "target_z": -1.0937500407507417, "ce": 6.316492557525635, "genuineness": 4.457139015197754, "identity": 0.7422775030136108, "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/vn_VOLT_reg_high/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "05c1ff484dbc4dd5da6ffd06f8e040237b7aa7dd65696f029169ef3643b6e9c1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "125a8e211d4323614777e7c117d35d377ed2741f6031068318f06084e85b3016", "generation_seconds_batch": 20.694394443999045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1280517578125, "target_z": -0.6406248552276287, "ce": 5.2640886306762695, "genuineness": 3.860914945602417, "identity": 0.5066543221473694, "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/vn_VOLT_reg_high/05c1ff484dbc4dd5da6ffd06f8e040237b7aa7dd65696f029169ef3643b6e9c1.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "060145594a78c8c60014fc5a591f525ae089c74a15ac394f44d137003eb0b3a4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c485595067a01900311c83db721211cb0249f3803301b3af8663f6279fb1028", "generation_seconds_batch": 21.59177334595006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.345165729522705, "target_z": -0.39062511260073324, "ce": 5.756534099578857, "genuineness": 3.973883628845215, "identity": 0.39876678586006165, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/060145594a78c8c60014fc5a591f525ae089c74a15ac394f44d137003eb0b3a4.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "069cc3f8445182012bfc5e31220946a989b14da78eeacdc034b3e2c82efb1ea6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "abc5c903edc68bbe9c513fc24cb94e827dcac5f4d20b6fb843adf350c7762d57", "generation_seconds_batch": 21.40668079594616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.380786180496216, "target_z": -0.34960931105886933, "ce": 5.254160404205322, "genuineness": 3.7040140628814697, "identity": 0.4871664047241211, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "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/vn_VOLT_reg_high/069cc3f8445182012bfc5e31220946a989b14da78eeacdc034b3e2c82efb1ea6.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "06d2d59bc4303a800a6184e8377299de7a8e63c73b9c703ca25a2d5c993807b6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0c4232d534746bc479e777688f6b6ee429d6791d8be3e7e8dc5b8182cad41c88", "generation_seconds_batch": 20.761833520955406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8600512742996216, "target_z": -0.9492187765416014, "ce": 6.0305562019348145, "genuineness": 4.300237655639648, "identity": 0.6340500712394714, "hypothesis": "La porte 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/vn_VOLT_reg_high/06d2d59bc4303a800a6184e8377299de7a8e63c73b9c703ca25a2d5c993807b6.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "07ec48bbc7e374a8fc3975724b35b845cd69f0c74aac538d4071255dc3fe7cf6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e60fe60bfbc068488c94b78773af2938be21af2752a6ac17307dae9e2b7c762", "generation_seconds_batch": 21.768480589031242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1484060287475586, "target_z": -0.6171875680966339, "ce": 6.1020402908325195, "genuineness": 4.319066047668457, "identity": 0.5629643201828003, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/07ec48bbc7e374a8fc3975724b35b845cd69f0c74aac538d4071255dc3fe7cf6.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "08ba58b99a53e1585d4eabc6e3cf20303175a771f7d79d26605571185f90016c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53b0956611d504d884e3043e6c0a1e3be6724ee5a1ce03eaa1cfd0527b401e08", "generation_seconds_batch": 15.445074496907182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9414691925048828, "target_z": -0.8554686671580319, "ce": 6.205295085906982, "genuineness": 4.250029563903809, "identity": 0.6225141286849976, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/08ba58b99a53e1585d4eabc6e3cf20303175a771f7d79d26605571185f90016c.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": "08fbaa3985ff6ac1ea54c1a83c2d9a809f01e73c22e09aea30fd65f0e46d4a0e", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "09a26c57014294a11e44ff1aeed7b2f18227a8baa74ec67a1404238e3880798c", "generation_seconds_batch": 15.28273417998571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.781090497970581, "target_z": 0.1113282119974713, "ce": 6.09409761428833, "genuineness": 3.9425034523010254, "identity": 0.5745824575424194, "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/vn_VOLT_reg_high/08fbaa3985ff6ac1ea54c1a83c2d9a809f01e73c22e09aea30fd65f0e46d4a0e.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "094205a70d36cebfd22de608501db4f9357e8d83f5b89a77cda9f5d35baf4a4c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "37c72a9d460ff0e77baa5fbb9c67f61f7909e6e43fc34eaa5d80bf58e66cb7d4", "generation_seconds_batch": 21.002210128004663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.005924940109253, "target_z": -0.7812499506701549, "ce": 6.165581703186035, "genuineness": 4.2374773025512695, "identity": 0.6335921883583069, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/094205a70d36cebfd22de608501db4f9357e8d83f5b89a77cda9f5d35baf4a4c.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "09ac87ee1211638a374ffb418a3d053387e1792ad0d7ff58563a597484db8d0e", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5fd6c6f41e72d0086f36746c4ba508ab3c603d5e05ed369ccd5024e48627e41b", "generation_seconds_batch": 15.686770553002134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4699242115020752, "target_z": -1.3984375187667888, "ce": 6.23706579208374, "genuineness": 4.406930446624756, "identity": 0.6386867761611938, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/09ac87ee1211638a374ffb418a3d053387e1792ad0d7ff58563a597484db8d0e.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "09acdf821b8c9e5f295d8b612e18d118581be7770874b9a663e7d1bec8831eeb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "988ff772649a220f3c89d4990cc18f73d55a215d36074500cbba5126713b9e74", "generation_seconds_batch": 22.287601656047627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.213622570037842, "target_z": 0.6093749560320947, "ce": 5.6254801750183105, "genuineness": 3.7793264389038086, "identity": 0.6096039414405823, "hypothesis": "La porte 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/vn_VOLT_reg_high/09acdf821b8c9e5f295d8b612e18d118581be7770874b9a663e7d1bec8831eeb.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "09d5d54c4e24214cb6eb4b53525180324cebef38cc0b54303ab36959ab537231", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5f0d80107022c000a1d79b17fb58940cdeb06b20b0414252b2415934b9fb3e86", "generation_seconds_batch": 15.413547935080715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.524202823638916, "target_z": -1.3359374458444093, "ce": 6.356205940246582, "genuineness": 4.432034492492676, "identity": 0.3791351318359375, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/09d5d54c4e24214cb6eb4b53525180324cebef38cc0b54303ab36959ab537231.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "0a206d4e918240550d7af7a9bc1c115922a682fe16aae94c714d13d19f27df26", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2c748b811870571974b4c90d163d422a56549f03dc68102f7770a1c6c80c5447", "generation_seconds_batch": 15.292809414095245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5716965198516846, "target_z": -1.2812499849865688, "ce": 6.078212261199951, "genuineness": 4.519899368286133, "identity": 0.7914779186248779, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0a206d4e918240550d7af7a9bc1c115922a682fe16aae94c714d13d19f27df26.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": "0a258f5b265c6dfa1fbfba75608802d89bc64b936a31c5066182c3d6439addd5", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "fc45332aae2001d1c8f52c0e5f25be4f89a0b3b5c3ca42a813dc3d89f8652eba", "generation_seconds_batch": 15.28273417998571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6996726989746094, "target_z": 0.017578239879557624, "ce": 6.062326908111572, "genuineness": 3.8922953605651855, "identity": 0.6036642789840698, "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/vn_VOLT_reg_high/0a258f5b265c6dfa1fbfba75608802d89bc64b936a31c5066182c3d6439addd5.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "0a43f328707e9d1b9f636d27ff444957ae0b37a09ba8a764bbce703232582044", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5664f31c4f5c51f9f337722e831d4239495f628e3b34bfce4005ff96ecdc3057", "generation_seconds_batch": 15.871326908003539, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.125868320465088, "genuineness": 4.243753433227539, "identity": 0.6493929624557495, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0a43f328707e9d1b9f636d27ff444957ae0b37a09ba8a764bbce703232582044.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "0a81e966561eeb37608a75c6e89e5d92beac3cc14ff2b8fe9abc531919f7832c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "812f1d6eed4f6e23be466885c11eff7da5b7f527cd5eea13a09d0deba238abe3", "generation_seconds_batch": 21.392650768975727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.250178337097168, "target_z": -0.5000000343164139, "ce": 6.173524379730225, "genuineness": 4.061748504638672, "identity": 0.8070335388183594, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0a81e966561eeb37608a75c6e89e5d92beac3cc14ff2b8fe9abc531919f7832c.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": "0ab8cf9d9f4fe35993d8b12f0d09d7d39e23df4af5b8e77bb457187f57f03360", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Someone moved the little blue chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7dfbed4e424d9052d123f6f14f4f772092044eb8855312c9548360b6385ebdcb", "generation_seconds_batch": 15.443227391922846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.375697612762451, "target_z": -0.355468632841618, "ce": 6.0305562019348145, "genuineness": 3.8671910762786865, "identity": 0.489187091588974, "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/vn_VOLT_reg_high/0ab8cf9d9f4fe35993d8b12f0d09d7d39e23df4af5b8e77bb457187f57f03360.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": "0b4db4bfb85853f276e128de9987b7ec7086e03c053491ec737fe1c056c523da", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0bd3806c393ff15439ab1714f0832e9f41095d25b18bc32ea1038621a864a1c2", "generation_seconds_batch": 21.110895602963865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.824343681335449, "target_z": 0.16113285894780247, "ce": 6.070269584655762, "genuineness": 3.8797430992126465, "identity": 0.46821409463882446, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la. en daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0b4db4bfb85853f276e128de9987b7ec7086e03c053491ec737fe1c056c523da.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "0b9afb4974bd7432b59488cb34e06c0f1f2a14e675f34163c2d31f7045e1142e", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6aa86219949fc71d1a42deb20987263e136be9bc1db22994625ead178e8cf2e7", "generation_seconds_batch": 15.366104502929375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.374936819076538, "target_z": -1.5078124404824695, "ce": 5.871703147888184, "genuineness": 4.055472373962402, "identity": 0.6085164546966553, "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/vn_VOLT_reg_high/0b9afb4974bd7432b59488cb34e06c0f1f2a14e675f34163c2d31f7045e1142e.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "0bcd8763c7e150d16416b0931170fde33249698809f80a422faa36c600494034", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1b10c7dc7f1dbee3ed6540b98cd23c0524132044c82906d55c6fb14044fc8de1", "generation_seconds_batch": 20.534251290024258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6056206226348877, "target_z": -1.2421874737264955, "ce": 6.109982967376709, "genuineness": 4.519899368286133, "identity": 0.6180839538574219, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0bcd8763c7e150d16416b0931170fde33249698809f80a422faa36c600494034.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": "0c1e2210a05f46c8af184f8cbb8abd80cecfad8755e5776fd7038df749fa7696", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c57bbd774271902c738b96ded7e275b8139c1d7a58696d3bb32783cad45a3cbc", "generation_seconds_batch": 21.544400686980225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3672165870666504, "target_z": -0.36523426065663633, "ce": 6.086154937744141, "genuineness": 4.080576419830322, "identity": 0.5191860198974609, "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/vn_VOLT_reg_high/0c1e2210a05f46c8af184f8cbb8abd80cecfad8755e5776fd7038df749fa7696.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": "0c70faee74b29feff203ff25e2f47beb48dc82709edf1bc322739901670d5d87", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I wrote the number on the envelope.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "c4847ad91568d79f32f5d31e70c4fcb8e319c4e3219971b77f2bb52f4adb7c5f", "generation_seconds_batch": 14.84915618703235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8973677158355713, "target_z": -0.9062500965149142, "ce": 6.308549880981445, "genuineness": 3.8044304847717285, "identity": 0.47320491075515747, "hypothesis": "I wrote the number on the envelope. Ride it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0c70faee74b29feff203ff25e2f47beb48dc82709edf1bc322739901670d5d87.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "0c7a5315b1bb9e5a4c3a5b88e31d1e888ce2b8b16f59fe5624e20fac5f478fc1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b79d2bfeb3de529f1488a35fb6bcf622dc06547c62e5072d091c898dc35a07f2", "generation_seconds_batch": 15.539590282016434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.272228956222534, "target_z": -0.4746094569036286, "ce": 5.935244083404541, "genuineness": 3.986435890197754, "identity": 0.5534932613372803, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro de la caja.", "wer": 0.17647058823529413, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0c7a5315b1bb9e5a4c3a5b88e31d1e888ce2b8b16f59fe5624e20fac5f478fc1.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "0c9effb701bd277576f2477844081844133fb138fff1de2a19ae41405ee16bd6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5d5b6eb633f92f4f3b0a9170f5a10cdde031cf324df1b848d12165a0b3c8b25e", "generation_seconds_batch": 15.805396878975444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.101673126220703, "target_z": 0.4804687786863773, "ce": 5.871703147888184, "genuineness": 3.6663577556610107, "identity": 0.530267596244812, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0c9effb701bd277576f2477844081844133fb138fff1de2a19ae41405ee16bd6.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "a40b1b892f582cf3553c1bdf97209df79ce765ae059c3a1be395e421bf5b454c", "generation_seconds_batch": 15.744588024914265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7548866271972656, "target_z": -1.0703124790884353, "ce": 6.006728172302246, "genuineness": 4.256305694580078, "identity": 0.7133069038391113, "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/vn_VOLT_reg_high/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "0ceddb9fc11bdbc52f9e3154f5dd8a9676ef2d7b33468e9dae44fe412ec9e6f6", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2aef71c3bdd3b8255936c0d48357ec4eb7f7bba6ab778c4f5596cc55b23cb207", "generation_seconds_batch": 15.445074496907182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.734532117843628, "target_z": -1.0937500407507417, "ce": 6.133810997009277, "genuineness": 4.306513786315918, "identity": 0.6461571455001831, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0ceddb9fc11bdbc52f9e3154f5dd8a9676ef2d7b33468e9dae44fe412ec9e6f6.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "0cff447d1c811a7b1053b0ef9e53e544f94a215a2650f2bbdcfcbd2a03e73f36", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3db5b5686642da99366fe757729733a6b7e315698473be7c3cdddba175e195cf", "generation_seconds_batch": 21.17097608698532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.915090560913086, "target_z": 0.26562496675597397, "ce": 6.157639026641846, "genuineness": 3.8546390533447266, "identity": 0.6505805253982544, "hypothesis": "Ik 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/vn_VOLT_reg_high/0cff447d1c811a7b1053b0ef9e53e544f94a215a2650f2bbdcfcbd2a03e73f36.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "0d6276a5574eb6da61f73f015d910b6f28239289ee1c9618a26089d87fd3bab2", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "00a0c2b5aa7db56b3a50fcf577e1781ee7147ffb28ed881a5ce6011052f3d87f", "generation_seconds_batch": 20.924085226026364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7403814792633057, "target_z": 0.06445308867285868, "ce": 5.9431867599487305, "genuineness": 4.111956596374512, "identity": 0.6030973196029663, "hypothesis": "La porte 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/vn_VOLT_reg_high/0d6276a5574eb6da61f73f015d910b6f28239289ee1c9618a26089d87fd3bab2.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "0d74ce37808b5408bef34b9f99b5ae915da0d03970949b39c72b855c301d266d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6adc493b9bc8358d349f29692d08950de79166db8b28fe9fe6a8010579b4abc0", "generation_seconds_batch": 19.492545088985935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8973677158355713, "target_z": -0.9062500965149142, "ce": 6.173524379730225, "genuineness": 4.268857479095459, "identity": 0.3984675407409668, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0d74ce37808b5408bef34b9f99b5ae915da0d03970949b39c72b855c301d266d.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "0d98535623c6acc385b75154ae0a98a4bf3ff1ecdc1f022c3044aaee9de70345", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c04b438d20e90cfe90098cfc04b7be5aa56ceb2049078ebbdcd8fc870196bbe2", "generation_seconds_batch": 15.379773881984875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.009317398071289, "target_z": -0.7773436446378853, "ce": 6.062326908111572, "genuineness": 4.444586753845215, "identity": 0.273340106010437, "hypothesis": "De deur staat nog open. Ik heb je je jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0d98535623c6acc385b75154ae0a98a4bf3ff1ecdc1f022c3044aaee9de70345.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": "0de5d1893084869480356d6291ba633e7d2aebd424697684e4e397b9cbf6af16", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Escribí el número en el sobre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "582d5b20a294fcc0b4233cfe86169bf2f1c3519153b98ddb91ff7b611b333f8d", "generation_seconds_batch": 15.999250952969305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8159499168395996, "target_z": -1.0000000686328279, "ce": 6.157639026641846, "genuineness": 4.344170093536377, "identity": 0.6704475283622742, "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/vn_VOLT_reg_high/0de5d1893084869480356d6291ba633e7d2aebd424697684e4e397b9cbf6af16.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "0e467b99977a6bb6759dc87f291e27da2fa252a7fce7e0b5e28931f6b5115e86", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9378df3f700e125930856092ee349341831801ad3e6e169c1d08538d3940f4c4", "generation_seconds_batch": 19.724668285925873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8634437322616577, "target_z": -0.9453124705093318, "ce": 6.229123115539551, "genuineness": 4.124508857727051, "identity": 0.49271100759506226, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0e467b99977a6bb6759dc87f291e27da2fa252a7fce7e0b5e28931f6b5115e86.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "0ef044eea7976d148d64ef5259bf736c953b895b9032e91d73b41d44af52a28d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d7f2361d508354f9df24bccc2ceb8cd61c8555f5fdb61272ddd6f723352211fe", "generation_seconds_batch": 21.10749418591149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5232672691345215, "target_z": -0.1855469284853483, "ce": 6.0305562019348145, "genuineness": 4.2374773025512695, "identity": 0.6106124520301819, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0ef044eea7976d148d64ef5259bf736c953b895b9032e91d73b41d44af52a28d.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "0f30e808c024edb9ea83c53a42ef3e6c0ea3c0040b3409b60b93cc7bda354435", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2d5460e849c3a1fea36326d14ab91cafb1bffad1c6ad2b649eefade58643e35c", "generation_seconds_batch": 23.165007681935094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9007601737976074, "target_z": -0.9023437904826446, "ce": 6.1894097328186035, "genuineness": 4.457139015197754, "identity": 0.4685449004173279, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0f30e808c024edb9ea83c53a42ef3e6c0ea3c0040b3409b60b93cc7bda354435.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "0f33c348308a0b509dda3d4a69991441c89d2adac0516c7466aeb80b00dfe647", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f60ac6d1d9bf70592e563598d48d2cb4043437ca49802342d137ccb4ab218a33", "generation_seconds_batch": 16.534035066026263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2053163051605225, "target_z": -1.7031249967828361, "ce": 5.935244083404541, "genuineness": 3.9801597595214844, "identity": 0.6162478923797607, "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/vn_VOLT_reg_high/0f33c348308a0b509dda3d4a69991441c89d2adac0516c7466aeb80b00dfe647.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "0f642223778d6f8da6800ccf2eb04d2e24b87eca9e7628f26f2f289a1daf7bd4", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "54fa2ac600ac1c0682c7606bf76d6b0b8a2b8f99e809696f1a093139b03f5174", "generation_seconds_batch": 15.244100891053677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.436000108718872, "target_z": -1.437500030026862, "ce": 6.181467056274414, "genuineness": 4.595211505889893, "identity": 0.6687769889831543, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0f642223778d6f8da6800ccf2eb04d2e24b87eca9e7628f26f2f289a1daf7bd4.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "0f72f653a03bcfc2c0a2600898c27633bb23ce73db4bfa041b090b481f8ba696", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bde1c354addb58eaf395908bad698dcd84df7373873f74f75479f4918bb3859e", "generation_seconds_batch": 14.91561769193504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1374680995941162, "target_z": -1.7812500193029828, "ce": 6.197352409362793, "genuineness": 4.193545341491699, "identity": 0.6815009117126465, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0f72f653a03bcfc2c0a2600898c27633bb23ce73db4bfa041b090b481f8ba696.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "0fc50adf077b32ef9b903d2d843ce9d37e46ebc5a7749091875f6fc3d81aa70b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6641926fc89d61ad8da379e794cc31401b3b9661c5887cce538011d486cbeebb", "generation_seconds_batch": 21.341941136983223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6802536249160767, "target_z": -1.1562499764074654, "ce": 5.990842819213867, "genuineness": 4.444586753845215, "identity": 0.6529005765914917, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0fc50adf077b32ef9b903d2d843ce9d37e46ebc5a7749091875f6fc3d81aa70b.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": "0fd3fc9fb0b6b7638f5cb3bdae0a60d32b37858b3e085b02a003945a3c1835bf", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "115ccdc8a11e75725e3bdf2b936373e2fa2343455ba9c96a7d6caeb65d19d9a0", "generation_seconds_batch": 14.609633366926573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.426583766937256, "target_z": -0.296874865951508, "ce": 6.173524379730225, "genuineness": 3.8169827461242676, "identity": 0.5755704641342163, "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/vn_VOLT_reg_high/0fd3fc9fb0b6b7638f5cb3bdae0a60d32b37858b3e085b02a003945a3c1835bf.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "0fda70da95263dc7472359b077b8a83324b8bdf807f711641862a2217010d0da", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e9c670a6aefc4dc5ae6c62f15e27e13f62d5740e3ad780c3fff10e25501c265f", "generation_seconds_batch": 20.582374951103702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.039849042892456, "target_z": -0.7421874394100816, "ce": 6.2767791748046875, "genuineness": 4.243753433227539, "identity": 0.6724690198898315, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/0fda70da95263dc7472359b077b8a83324b8bdf807f711641862a2217010d0da.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "1026bd144b9ccea16881cc06aa89c5b758aaffe17b8fbe266f05bd117da99123", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2bbd1c0f2dca560fa31aa218265605f82215f01ea263ea8122fe7d9fa423da76", "generation_seconds_batch": 14.133097704965621, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3706088066101074, "target_z": -0.36132822915567825, "ce": 6.141753673553467, "genuineness": 4.005263805389404, "identity": 0.7412481904029846, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1026bd144b9ccea16881cc06aa89c5b758aaffe17b8fbe266f05bd117da99123.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "106aa9edef584a19a17351fa2f22f356de3464f98780be71b9388d8cc7b0f4af", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3a0a94645f53c013478d0b63361b473f721b6d949e2e58588732c99b63c70275", "generation_seconds_batch": 15.490249214926735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.094127655029297, "target_z": -0.679687366487702, "ce": 6.054384231567383, "genuineness": 4.20609712600708, "identity": 0.42399832606315613, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/106aa9edef584a19a17351fa2f22f356de3464f98780be71b9388d8cc7b0f4af.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "1078cf81f7f43fb98277e4e9fde5d06fffd6ac4b40a004aa633724f036bc5d33", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f330da28c28b72942c0b586e3bf2dbc0e5fc2ec113eabdac1b8fd812fc254311", "generation_seconds_batch": 20.205279950983822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5309876203536987, "target_z": -1.3281249710455256, "ce": 6.117925643920898, "genuineness": 3.7918784618377686, "identity": 0.32568174600601196, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1078cf81f7f43fb98277e4e9fde5d06fffd6ac4b40a004aa633724f036bc5d33.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": "109791cbd710ec5410ce6211353420c39fba46bd89da903b8b46b763e6fc5288", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa6303b65d7e62d544345d4519423a4cfd9dfe629cd6ee9254ad07732156fdc5", "generation_seconds_batch": 20.661556364037097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8743817806243896, "target_z": 0.21875011796267294, "ce": 5.855817794799805, "genuineness": 3.8922953605651855, "identity": 0.6056972146034241, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos comer.", "wer": 0.05, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/109791cbd710ec5410ce6211353420c39fba46bd89da903b8b46b763e6fc5288.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "116c0288fd356a5306bc3da92a7ace781839fad3c0286d99d86c79a378972392", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f7fd4855107b6339f0c67444abf09069167c63e4764b83478605afcf29bf747b", "generation_seconds_batch": 20.858146449900232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1238985061645508, "target_z": -1.79687496890075, "ce": 6.1894097328186035, "genuineness": 3.8671910762786865, "identity": 0.29096171259880066, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/116c0288fd356a5306bc3da92a7ace781839fad3c0286d99d86c79a378972392.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": "1172c5c74b4e534cb164af7a882f80ebdc6bc6e4a6429d5b2bf0a208f49ab642", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a2b8c7f91054a9bd7575c5f63562ca4db63fe6d5cf3f3dc88191ef79d302ce13", "generation_seconds_batch": 14.364586618030444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1382288932800293, "target_z": -0.6289062116621313, "ce": 6.23706579208374, "genuineness": 4.331617832183838, "identity": 0.7292470932006836, "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/vn_VOLT_reg_high/1172c5c74b4e534cb164af7a882f80ebdc6bc6e4a6429d5b2bf0a208f49ab642.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "1193db24671e9152915fa6439d7511b34976cba3ab0ced208ef4176ca008fce1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7046b69a079b9d62ed810c85fe973574d7df64ff20edc69aabd0115d7d89928", "generation_seconds_batch": 17.007827472058125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8099257946014404, "target_z": 0.14453112694348436, "ce": 5.998785495758057, "genuineness": 3.785602569580078, "identity": 0.6741628050804138, "hypothesis": "La porte 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/vn_VOLT_reg_high/1193db24671e9152915fa6439d7511b34976cba3ab0ced208ef4176ca008fce1.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "11a3660ccee8a6c33efd92f6c8d0a426694d38df1a56de6b23aee927c3586d58", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "da7aadce61e8106886dfd9900aa41e947a425fe73fdc21b3505f14adbcb8b9bb", "generation_seconds_batch": 16.18445148295723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.039849042892456, "target_z": -0.7421874394100816, "ce": 6.141753673553467, "genuineness": 4.168440818786621, "identity": 0.5384459495544434, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/11a3660ccee8a6c33efd92f6c8d0a426694d38df1a56de6b23aee927c3586d58.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "11cf0f5f16dcf6bd52d90cf2fa692a08d020644b6fe2e155a89144c8f446322a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fcbea24eb5d84f2719c379d261e411bd737aa2aa409343aa72f6982639ba5e59", "generation_seconds_batch": 20.974997066077776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0356957912445068, "target_z": -1.8984375530832027, "ce": 6.205295085906982, "genuineness": 3.7416701316833496, "identity": 0.36809539794921875, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/11cf0f5f16dcf6bd52d90cf2fa692a08d020644b6fe2e155a89144c8f446322a.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "120557c1a4ae5d9010de33418225022e7a1a6f58ec5bdea49923aa50039fd89a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e0c4f631d2b82530b6d289c3543c78a74387aa898b0555ec2a0d30a948cd463b", "generation_seconds_batch": 15.712529059965163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1789379119873047, "target_z": -0.5820310883375187, "ce": 6.141753673553467, "genuineness": 4.507347106933594, "identity": 0.5455183386802673, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/120557c1a4ae5d9010de33418225022e7a1a6f58ec5bdea49923aa50039fd89a.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "123c141ae9aecbade2e6a5d1c462e09648d810f405dc4a1eb99bbc3820e4551c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6db4548779f906c9df5cb9cf342ac2637cc042982fb8ecd137bc5cf5b1818f68", "generation_seconds_batch": 20.481646318919957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3900279998779297, "target_z": 0.8125001243970006, "ce": 5.458683967590332, "genuineness": 3.9927117824554443, "identity": 0.35593080520629883, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/123c141ae9aecbade2e6a5d1c462e09648d810f405dc4a1eb99bbc3820e4551c.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "860f2084408c73136ad830604c179b249fefc69d25a90e6a58ef19fe9566f6f2", "generation_seconds_batch": 15.720845017000102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6395447254180908, "target_z": -1.2031249624664222, "ce": 6.173524379730225, "genuineness": 4.419482707977295, "identity": 0.5893372297286987, "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/vn_VOLT_reg_high/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "130108aa4e0e0dc65b6d9ba6b0e1826185b834f9dbb2e4559af88691e3843222", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5775649196f7ee0486487c2b1c25308921726a0820c0ce0991ce4a9ecc94055f", "generation_seconds_batch": 20.138115223962814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.948253870010376, "target_z": -0.8476563296248042, "ce": 6.229123115539551, "genuineness": 4.419482707977295, "identity": 0.4229850172996521, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/130108aa4e0e0dc65b6d9ba6b0e1826185b834f9dbb2e4559af88691e3843222.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "13271d9eeee07d5b9d325c8502a60e814e198dad6d0433d37811b8dd909f10e3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c25c004995554bc5ca3908615f4565c70de150759efd2b5b71562103ef351bba", "generation_seconds_batch": 25.34119206201285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7548866271972656, "target_z": -1.0703124790884353, "ce": 6.181467056274414, "genuineness": 4.356721878051758, "identity": 0.6486080884933472, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/13271d9eeee07d5b9d325c8502a60e814e198dad6d0433d37811b8dd909f10e3.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "1335b13abc4877dfaa1989c8673d180cbfb88fb7921eb44f2db1c54084e1647c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cb0a1b778daad9f1faff388c286b017f0a2b5d3bfb01f089032d4f3205591ca1", "generation_seconds_batch": 21.675333639024757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4563546180725098, "target_z": -1.414062468364556, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.601813554763794, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1335b13abc4877dfaa1989c8673d180cbfb88fb7921eb44f2db1c54084e1647c.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": "134ce48a370aa78ca963672f6f2686ca0f22df37d0de2ab5bcd57e224ab2fd84", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The keys are on the kitchen table.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ff89f15ae9ea5d4e89c36f8e5540265251b79af5000133f4596bcdfa08e2753", "generation_seconds_batch": 23.53854424401652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5385332107543945, "target_z": -0.16796868860579067, "ce": 5.982900142669678, "genuineness": 3.8044304847717285, "identity": 0.4716891646385193, "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/vn_VOLT_reg_high/134ce48a370aa78ca963672f6f2686ca0f22df37d0de2ab5bcd57e224ab2fd84.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "139c476c6c164c7a2f8a83b15077845c4503d406520d782af0c1e9ad5a80dcc6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "41f47ffc1a29f43d9437aa024d4d0a34c3ee602d5d6931ee5db5e8efb317ac29", "generation_seconds_batch": 20.665254767984152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.830280303955078, "target_z": 0.16796868860579067, "ce": 5.194590091705322, "genuineness": 3.7793264389038086, "identity": 0.5008715987205505, "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/vn_VOLT_reg_high/139c476c6c164c7a2f8a83b15077845c4503d406520d782af0c1e9ad5a80dcc6.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "13ba6986cd5d8be992af371d3634b95e3f38ac670ee0b627cb778b28c83222b7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8bad846f604dfc68a2022f3f217e63b5e061280174e78aa61733df1527083bfa", "generation_seconds_batch": 21.289261717931367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5605838298797607, "target_z": -0.1425781111930053, "ce": 6.070269584655762, "genuineness": 4.281409740447998, "identity": 0.5709255933761597, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/13ba6986cd5d8be992af371d3634b95e3f38ac670ee0b627cb778b28c83222b7.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "13ff9f28da3b9b87f130da500b0f31586681152b71d9725507de21a466e0c650", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "976096307d72064b2b499769bfab771f68255c65eb844d88419ace1ab0c72807", "generation_seconds_batch": 15.479837257997133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5445572137832642, "target_z": -1.3125000214477587, "ce": 6.1020402908325195, "genuineness": 4.400654315948486, "identity": 0.5716893672943115, "hypothesis": "En que he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro de la casa.", "wer": 0.29411764705882354, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/13ff9f28da3b9b87f130da500b0f31586681152b71d9725507de21a466e0c650.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "14360ec5585f04d9b4be7e7e96746d6e66bddae66fb4a9b773b8ce754fba5ebc", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5c74daf2daa85c0bd66bf22c4c45dc0e7e165fd02ca33f8623a486253e899218", "generation_seconds_batch": 19.48051356105134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.158583402633667, "target_z": -0.605468649999825, "ce": 6.221180438995361, "genuineness": 4.2751336097717285, "identity": 0.5269806385040283, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/14360ec5585f04d9b4be7e7e96746d6e66bddae66fb4a9b773b8ce754fba5ebc.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": "144bae91ed3f0e20c823a096f75747c688533adf7ce5c47e57f339d785e3410c", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Escribí el número en el sobre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4239626f5635424e64362762c8bcfe36fdd6ef62872bbea568067447fd9fdc0", "generation_seconds_batch": 13.616705731023103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2586593627929688, "target_z": -0.4902344065013956, "ce": 5.597680568695068, "genuineness": 3.8420867919921875, "identity": 0.7368876338005066, "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/vn_VOLT_reg_high/144bae91ed3f0e20c823a096f75747c688533adf7ce5c47e57f339d785e3410c.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "145194a30fc7fb3b3659c3b4f61a7a004a0882db94a8f1a3147481f9471bcf5b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "acaa3524dbd6712acb8727e8e09c1624e349082fbe8ed96c57bb6bf0d7a123c8", "generation_seconds_batch": 21.63147620402742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5935723781585693, "target_z": 1.046874917426129, "ce": 5.700935363769531, "genuineness": 3.6098732948303223, "identity": 0.4045962691307068, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/145194a30fc7fb3b3659c3b4f61a7a004a0882db94a8f1a3147481f9471bcf5b.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "1479d6a7f52b6125d2c415a1590f3e1259bc8b9453d4c9e13eed61a8267df34f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ed3d320388e7e749ea8d772b9caa315c02d2b25d7cec61f39c0e155bf988a8bd", "generation_seconds_batch": 20.105729968985543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6124054193496704, "target_z": -1.234374998927612, "ce": 6.1894097328186035, "genuineness": 4.319066047668457, "identity": 0.7257896661758423, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1479d6a7f52b6125d2c415a1590f3e1259bc8b9453d4c9e13eed61a8267df34f.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "14fb8ac51222665ab135625b6fbb4266cdd6136439db9ec63d96f533cfd7c5af", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "052e1b649355ea63a32e069c10cfdcd234ac4c4d4dad412a7485efe3736ff10f", "generation_seconds_batch": 15.235562562011182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063595771789551, "target_z": -0.7148438462468173, "ce": 6.117925643920898, "genuineness": 4.13078498840332, "identity": 0.7635729312896729, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/14fb8ac51222665ab135625b6fbb4266cdd6136439db9ec63d96f533cfd7c5af.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": "151ea8493df1737901b739ecaeabc426092917b37168d244e3f4c36f917845c4", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Escribí el número en el sobre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "9f7b335563e9472e38bc7bcd07cdd86726cca9d1e497c1660b9f52ecd2e87d19", "generation_seconds_batch": 15.999250952969305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1110897064208984, "target_z": -0.6601561108576653, "ce": 6.23706579208374, "genuineness": 4.256305694580078, "identity": 0.7036566138267517, "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/vn_VOLT_reg_high/151ea8493df1737901b739ecaeabc426092917b37168d244e3f4c36f917845c4.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "71caa992c5802c0eb5e4b60e4a6eafb6b19a4f967a2d0556b766d68d0e3378de", "generation_seconds_batch": 14.992098537040874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4292153120040894, "target_z": -1.4453125048257458, "ce": 6.316492557525635, "genuineness": 4.293961524963379, "identity": 0.6227929592132568, "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/vn_VOLT_reg_high/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "15df063ab49573863d6d2ffec8fe96fccbc2e3f426d42d0dba22243273c8d8b7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a54c874bf17c4edcfc97eeed7504b69a32db12c86d26e989fe4dbb81270fc683", "generation_seconds_batch": 20.098065205966122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8023803234100342, "target_z": -1.0156250182305948, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.5233542323112488, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/15df063ab49573863d6d2ffec8fe96fccbc2e3f426d42d0dba22243273c8d8b7.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "16442e0fbd710fd5a254231db1689b774e6da4e2a559c95f41b66847d551e4f2", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8161b0a5a74427aafeb7d9503074518ec155622eb16951f4bdfc924dd7e165d8", "generation_seconds_batch": 16.02544629503973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3817216157913208, "target_z": -1.499999965683586, "ce": 6.308549880981445, "genuineness": 4.18726921081543, "identity": 0.47072914242744446, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/16442e0fbd710fd5a254231db1689b774e6da4e2a559c95f41b66847d551e4f2.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "164a7f627e027311950234fbcf3c2969d70e1d047e2955e16fe305fae43625df", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "845dd6c0c77e80c861599043c71e1940c7ddfbff325a40deabbe85e292c8c27d", "generation_seconds_batch": 15.227561134030111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5309876203536987, "target_z": -1.3281249710455256, "ce": 6.24500846862793, "genuineness": 4.256305694580078, "identity": 0.5059951543807983, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/164a7f627e027311950234fbcf3c2969d70e1d047e2955e16fe305fae43625df.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "167ed636813d4e32823d2e495763c3b0e15acd4adc1bd3b1cf4ee21d560ff016", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2093acb5eb06f6002e1b29818bb9be27779e055e7170f7901feab3c3b3c13b7", "generation_seconds_batch": 16.57208705402445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1721529960632324, "target_z": -0.589843700402058, "ce": 6.1020402908325195, "genuineness": 3.9048471450805664, "identity": 0.4129694700241089, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vie fenêtre. We've regarded ensemble what contiened.", "wer": 0.3684210526315789, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/167ed636813d4e32823d2e495763c3b0e15acd4adc1bd3b1cf4ee21d560ff016.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "168895309f5632b50f31c22e668c4238f27adf7a979309793e021d3228b85985", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cf4aee852293161bf10453d498d365ce4b2fd79e45841da9ab782ff21046c3dd", "generation_seconds_batch": 23.42366203002166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1144819259643555, "target_z": -0.6562500793567072, "ce": 6.197352409362793, "genuineness": 4.18726921081543, "identity": 0.6531162261962891, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/168895309f5632b50f31c22e668c4238f27adf7a979309793e021d3228b85985.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "175acd59c72a833a502b1c476a3fcf1fe151771121ae1eca394ce9a7a70181f2", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "464423ea420eb817b6b8de65236bd74a0dc7f2b0a1e8301492e0ad07d1554f15", "generation_seconds_batch": 16.230296044959687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.893887996673584, "target_z": 0.24121089721842817, "ce": 5.871703147888184, "genuineness": 3.6663577556610107, "identity": 0.3108333349227905, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/175acd59c72a833a502b1c476a3fcf1fe151771121ae1eca394ce9a7a70181f2.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": "1798b82e0433106c3c6e440f554dbb69730d80da1a22b62f53357a8715522f7b", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c79ef9a91656e3d05581846d81383dd798366df748f6123784df42d55281f1ec", "generation_seconds_batch": 21.708768471027724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9312918186187744, "target_z": -0.8671875852548409, "ce": 5.796247482299805, "genuineness": 3.9173994064331055, "identity": 0.2985439896583557, "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/vn_VOLT_reg_high/1798b82e0433106c3c6e440f554dbb69730d80da1a22b62f53357a8715522f7b.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "17afa99f6df6fe317099938b0e7b1112e5c356d15e819eb354a814a578a278c6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d8b447693a0b03815ace62ebcb8834c6d09b51fea3dc60b29dc38c69c41d7c3a", "generation_seconds_batch": 24.13415482104756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2433934211730957, "target_z": -0.5078126463809532, "ce": 6.0305562019348145, "genuineness": 3.9927117824554443, "identity": 0.7615764737129211, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/17afa99f6df6fe317099938b0e7b1112e5c356d15e819eb354a814a578a278c6.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "17c400ee3611a4b850451ac9d89b407c87faf80a8e26b2518c746ba0caa1fb84", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0b758761bddbdbf6145a28cde752855f86e8a51013b479ec97b6214cacb2f68d", "generation_seconds_batch": 21.224263992044143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4130139350891113, "target_z": -0.3125000900805866, "ce": 6.125868320465088, "genuineness": 4.6956281661987305, "identity": 0.5085030794143677, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/17c400ee3611a4b850451ac9d89b407c87faf80a8e26b2518c746ba0caa1fb84.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "17e6d6738938000be1c79ba13fde8a5c56d3fb381a7a003db472d26b1a45fb3f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5f49658dc1a32f3eee0242ca335ac056650f9ccbff2161f6f7ad9ce37bee5e90", "generation_seconds_batch": 20.869164578965865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.975393295288086, "target_z": -0.8164061558979586, "ce": 5.927301406860352, "genuineness": 4.068024158477783, "identity": 0.3789215087890625, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/17e6d6738938000be1c79ba13fde8a5c56d3fb381a7a003db472d26b1a45fb3f.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "17eacbd27fbe6f8d778d175ad03515919f286248131e27e54ed79fd57e4ad50e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "994c90097394f495410f869f12979abda49044b93bf130a2a23acca3d0075cbc", "generation_seconds_batch": 14.714047441957518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.48764705657959, "target_z": -0.22656245549590068, "ce": 5.089349746704102, "genuineness": 3.6914620399475098, "identity": 0.547839343547821, "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/vn_VOLT_reg_high/17eacbd27fbe6f8d778d175ad03515919f286248131e27e54ed79fd57e4ad50e.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "17f223236f6cba54fbacf7ebebb46ba668f86c06c82645024efaa091c978fe7f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3496491eabacde684f026647849880b757e72221d41350a948435e780b8358f6", "generation_seconds_batch": 21.828391343005933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.059267997741699, "target_z": 0.4316406396112856, "ce": 6.1020402908325195, "genuineness": 3.7793264389038086, "identity": 0.663791298866272, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/17f223236f6cba54fbacf7ebebb46ba668f86c06c82645024efaa091c978fe7f.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "17f3c90a5d838fcbeef6695090f12fe17cb6a7f1c3f557e848eb1ee6670234c1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0501673e6dc2da397ebf5f0798e3466d1f7dd8928bc841eb8761b8e4ee29381b", "generation_seconds_batch": 20.578395624062978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.84308922290802, "target_z": -0.968750032171638, "ce": 6.308549880981445, "genuineness": 4.231201171875, "identity": 0.643205463886261, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/17f3c90a5d838fcbeef6695090f12fe17cb6a7f1c3f557e848eb1ee6670234c1.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "1816181ad0a9e77fa874c5c84dcde72927a59b138c06415192013b7ddc9710a0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e0acfd55a7d1a6891e01e1283becca01c8bde1cc965f3f8f8716f5048acf2197", "generation_seconds_batch": 20.174441277049482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.369673490524292, "target_z": 0.7890625627346942, "ce": 5.808161735534668, "genuineness": 3.6789097785949707, "identity": 0.6499011516571045, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1816181ad0a9e77fa874c5c84dcde72927a59b138c06415192013b7ddc9710a0.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "184aa40e7235aeaa93ae6b4070de1066de1c4a94eb98fc12753ae2a302938975", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f648d11d772f5f7b188dccbe6afab36a76774920fd7e50c4411bc48b4c06eefb", "generation_seconds_batch": 21.986977887921967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0287363529205322, "target_z": 0.39648443438348197, "ce": 6.133810997009277, "genuineness": 3.8169827461242676, "identity": 0.40483978390693665, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/184aa40e7235aeaa93ae6b4070de1066de1c4a94eb98fc12753ae2a302938975.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "185029793ca961cee8ae7b3631abb6cbc541bf15a5ee1f43f476d09d8a5b38fb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d3de9a7a96e12ab5039cb960b74fa840dd0528f6f775eab6b94eab3297e098d4", "generation_seconds_batch": 15.670838841004297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0602035522460938, "target_z": -0.7187498777477753, "ce": 5.585766792297363, "genuineness": 4.143336772918701, "identity": 0.42695513367652893, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/185029793ca961cee8ae7b3631abb6cbc541bf15a5ee1f43f476d09d8a5b38fb.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "188c7fe8ef1f57e8754027579de416daff1a4288286c606b317cacf5b3c94a54", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "73128624b6dbd033a1d18f8ab0de1c7648cac7b59f0e1d481a6050c3709db985", "generation_seconds_batch": 16.290545369964093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4970635175704956, "target_z": -1.3671874823055992, "ce": 6.213237762451172, "genuineness": 4.557555198669434, "identity": 0.5638149976730347, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/188c7fe8ef1f57e8754027579de416daff1a4288286c606b317cacf5b3c94a54.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "1904f6ced9ca9ff6320500329364c7c8e963742f42f8e50620e0e06f3ca6a529", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "be9f9726c0a0bbcc39531b599808aa4c83901028147985e1171902232528b9fa", "generation_seconds_batch": 15.646908047026955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.734532117843628, "target_z": -1.0937500407507417, "ce": 6.157639026641846, "genuineness": 4.149612903594971, "identity": 0.5385468006134033, "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/vn_VOLT_reg_high/1904f6ced9ca9ff6320500329364c7c8e963742f42f8e50620e0e06f3ca6a529.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "194a18180ae74eb5ff6cd0293f47dabe8d8dad9bc18447c5a6bc7d8624b5e40f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9311805938a5a3c2ab0badeb20a843f2da9578dde78a1af0d94e4c9c7095024c", "generation_seconds_batch": 20.653726221062243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.937141180038452, "target_z": 0.29101554416875935, "ce": 6.062326908111572, "genuineness": 3.7918784618377686, "identity": 0.5195701122283936, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/194a18180ae74eb5ff6cd0293f47dabe8d8dad9bc18447c5a6bc7d8624b5e40f.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "19848d144bd0ec82f049fcec090aef49337993bf6af59597cafd26e9504228ca", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f2134194182ded1d3ec8a217bd9ae28b7497b6a0fc1c6012c0347caa11da2643", "generation_seconds_batch": 20.974997066077776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5784813165664673, "target_z": -1.2734375101876854, "ce": 6.1020402908325195, "genuineness": 3.886019229888916, "identity": 0.4904913902282715, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/19848d144bd0ec82f049fcec090aef49337993bf6af59597cafd26e9504228ca.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "19981b21e00b563a6b8731cfccb8dc46d001e6793d95a04f96850514574f67e6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2942d491bdaaf3c5f5bea98d5af26b47b164e4b0213ff411b86bd87d0d865bc3", "generation_seconds_batch": 20.52745135407895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.509697675704956, "target_z": -0.20117187808311532, "ce": 5.669164657592773, "genuineness": 3.9801597595214844, "identity": 0.147101491689682, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/19981b21e00b563a6b8731cfccb8dc46d001e6793d95a04f96850514574f67e6.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": "199f4d0ef58c75efe12d5833b1203b5f386e31426f2fd4496a62043b377b5a21", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cf1122b9085efb89c76e1f96745e20c8fffcbaff711eff0e473e3aa5959545dd", "generation_seconds_batch": 21.11279060097877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5724573135375977, "target_z": -0.12890617734571735, "ce": 6.205295085906982, "genuineness": 4.080576419830322, "identity": 0.636043906211853, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grand bibliothèque. Nous la remetrons after le déjeuner.", "wer": 0.14285714285714285, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/199f4d0ef58c75efe12d5833b1203b5f386e31426f2fd4496a62043b377b5a21.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": "19d1446f17fa2c7091e71c36cc1fc7ee68c6e01cc64d74f637e886fe4dd74804", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "886041d6a9c1dfa6e6d01be21266b42773f3c18de8f700fff69641012e866ff3", "generation_seconds_batch": 13.766586395096965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8794703483581543, "target_z": 0.22460943974542164, "ce": 6.173524379730225, "genuineness": 4.011539936065674, "identity": 0.5502201318740845, "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/vn_VOLT_reg_high/19d1446f17fa2c7091e71c36cc1fc7ee68c6e01cc64d74f637e886fe4dd74804.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "1a08e2e0acc4387e99f507cd121a0213cc2012cde153127e2689ed36027860d6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a0c6e8166d0d0fe5cb890b8dcc145815d6c96b44370d06dedc9f64ed1dc87855", "generation_seconds_batch": 21.392650768975727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.272228956222534, "target_z": -0.4746094569036286, "ce": 6.062326908111572, "genuineness": 4.061748504638672, "identity": 0.6812171339988708, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1a08e2e0acc4387e99f507cd121a0213cc2012cde153127e2689ed36027860d6.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "1a260f750c97902fbeb962ef0dc3135405a17b720963a8209848692e15ecd296", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "19b1b41701522ae7e9cf64bc207bf2d3a3bc42e12eb1655ea019ddd5750e361e", "generation_seconds_batch": 19.736094641964883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9448615312576294, "target_z": -0.8515624983914181, "ce": 6.133810997009277, "genuineness": 4.457139015197754, "identity": 0.7331110239028931, "hypothesis": "La porte 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/vn_VOLT_reg_high/1a260f750c97902fbeb962ef0dc3135405a17b720963a8209848692e15ecd296.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": "1a3ac3d8953ff8a6b39ed4039dbb500fe29951002baf18c9c39277af45fc975c", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "55d8b829e6c588655eff744b7e20bb9495c60a03f0d16c9042c612254bc81b76", "generation_seconds_batch": 14.609633366926573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4961280822753906, "target_z": -0.21679682768088232, "ce": 6.348263263702393, "genuineness": 3.9048471450805664, "identity": 0.2592898905277252, "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/vn_VOLT_reg_high/1a3ac3d8953ff8a6b39ed4039dbb500fe29951002baf18c9c39277af45fc975c.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "1aa3494c37413cbb08e228915eee6071bdddd7d4c57f1b6e49aea9b4b6f323c7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "94a7008cfc3f54f5a8a7d3ba87e6b6191c9db9965b3c3f30080e1b0c5a7afc99", "generation_seconds_batch": 21.784027372021228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.257723808288574, "target_z": 0.6601561108576653, "ce": 6.0305562019348145, "genuineness": 3.848362922668457, "identity": 0.22894014418125153, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1aa3494c37413cbb08e228915eee6071bdddd7d4c57f1b6e49aea9b4b6f323c7.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "1aae74d9bbf85489be8f17f347a199d0b3e11edcd8976915f6ea5e5a54ad3b3c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "99909665f636ab9417ff702ff0d35b258a2ce32e34b9ca6b952e90e818cc63a7", "generation_seconds_batch": 15.616046765004285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5377724170684814, "target_z": -1.3203124962466422, "ce": 6.109982967376709, "genuineness": 4.482243061065674, "identity": 0.6874310970306396, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1aae74d9bbf85489be8f17f347a199d0b3e11edcd8976915f6ea5e5a54ad3b3c.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "1ab223568227b7e5e2c4a313a53b9fb2c56b518ac2231ead10d726dfbcdc8fcf", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "83af76e0ab612b8de5c70feff5f93a6147378041da717d2f7ebf53c93df6dd18", "generation_seconds_batch": 15.980390753014944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.524202823638916, "target_z": -1.3359374458444093, "ce": 6.038498878479004, "genuineness": 4.545003414154053, "identity": 0.558186948299408, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1ab223568227b7e5e2c4a313a53b9fb2c56b518ac2231ead10d726dfbcdc8fcf.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "1af91e5e1896f85ba0e4e64960cbacb8b494dc2d2dc9a2ad843718ed381ea055", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "67fe3c41ca0dfe3b4ed360a1b7a5a7184ab221a0b1f66f371d46e42fcbf23933", "generation_seconds_batch": 15.118541868054308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5300521850585938, "target_z": -0.177734316420809, "ce": 5.788304805755615, "genuineness": 3.8295347690582275, "identity": 0.5585219860076904, "hypothesis": "La porte 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/vn_VOLT_reg_high/1af91e5e1896f85ba0e4e64960cbacb8b494dc2d2dc9a2ad843718ed381ea055.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": "1bb643339439f42b0ad0c06c7780e46c52cc77711798840879168cae681752f4", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "92801f4cb568b1fa95168ddbf8b447e8bddc234d0a1111ad3e15b1290c3dd81a", "generation_seconds_batch": 16.91149204794783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1484060287475586, "target_z": -0.6171875680966339, "ce": 6.268836498260498, "genuineness": 4.482243061065674, "identity": 0.7404447197914124, "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/vn_VOLT_reg_high/1bb643339439f42b0ad0c06c7780e46c52cc77711798840879168cae681752f4.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "1c5aa0015ab3bafa6e38f4bbe489bdbc491d1b12611ab8fb117eef39c0d1ff0b", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e7c21e72483bb1d6f0c50fe68c0ca68c45d15349074f156742ec18adc7ab8019", "generation_seconds_batch": 15.517187390010804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.476709008216858, "target_z": -1.3906250439679053, "ce": 6.292664527893066, "genuineness": 4.582659721374512, "identity": 0.5988727807998657, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1c5aa0015ab3bafa6e38f4bbe489bdbc491d1b12611ab8fb117eef39c0d1ff0b.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "1c7e97334afa0e15be5fa8aea3ab7c0c704f3046da466b66f261ae8c38eaeb95", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f816c0dce27ff24870f369c7c62a88956aa86589212fb5d319a9b207a2e5272d", "generation_seconds_batch": 21.807995823095553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.598835825920105, "target_z": -1.249999948525379, "ce": 6.38003396987915, "genuineness": 4.231201171875, "identity": 0.3813168406486511, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1c7e97334afa0e15be5fa8aea3ab7c0c704f3046da466b66f261ae8c38eaeb95.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "1d1b6b8c38e444fae0afdeff1a98ebb98b0cba4778796411d369880c9301aa1c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9e15381f5cc5540ec0afefd8c34b8891be5f8c66cbb4ed4d997f5fdaedbf5e3c", "generation_seconds_batch": 15.54425799404271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5784813165664673, "target_z": -1.2734375101876854, "ce": 6.133810997009277, "genuineness": 4.3881025314331055, "identity": 0.7127455472946167, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1d1b6b8c38e444fae0afdeff1a98ebb98b0cba4778796411d369880c9301aa1c.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "1d22be375c8bcb37392645958cfe2218da6a52fb009cdfbe39d176584994421d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "aadc335fa23ecd47e6ff261e9a823ff08d8daf1a39cfaeb75cfd34b9050f7866", "generation_seconds_batch": 20.655509580974467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4699242115020752, "target_z": -1.3984375187667888, "ce": 5.871703147888184, "genuineness": 4.193545341491699, "identity": 0.5265580415725708, "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/vn_VOLT_reg_high/1d22be375c8bcb37392645958cfe2218da6a52fb009cdfbe39d176584994421d.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "1d2507ed35aafab8d5b5039c01e6244f2b2758be6f2403e98f1bcea74ad96555", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e8fd2267f46bd87052bfcf13e186ca23b06b8d2ad8b010c8198af5a319a50890", "generation_seconds_batch": 15.244100891053677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4224305152893066, "target_z": -1.4531249796246293, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.6426422595977783, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1d2507ed35aafab8d5b5039c01e6244f2b2758be6f2403e98f1bcea74ad96555.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "1d2987d356cd080f07504365c2b7cfbc5433708f5122aa53c37cf836a12b91c0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "daf4c11f5edb10329d6c061511f5473bfdd58dfa3d73d3384b211c74bbd701c8", "generation_seconds_batch": 21.22404270991683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6124054193496704, "target_z": -1.234374998927612, "ce": 6.173524379730225, "genuineness": 4.2751336097717285, "identity": 0.7396557331085205, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1d2987d356cd080f07504365c2b7cfbc5433708f5122aa53c37cf836a12b91c0.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": "1d54b61425645c9da66b14876b317810627eebbdbaa38873c26b4f4497a05e2e", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "48a0023abb197c515b4b01d82c012326494224a9e91cde093ebe163840e3721e", "generation_seconds_batch": 16.358327912981622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.734532117843628, "target_z": -1.0937500407507417, "ce": 5.959072113037109, "genuineness": 3.9299514293670654, "identity": 0.6974174380302429, "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/vn_VOLT_reg_high/1d54b61425645c9da66b14876b317810627eebbdbaa38873c26b4f4497a05e2e.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "c81cdb10adacd76ebc4814d761a9e333f0b1b971f1257b227902504770e2002a", "generation_seconds_batch": 15.282993925968185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.476709008216858, "target_z": -1.3906250439679053, "ce": 6.284721851348877, "genuineness": 4.2374773025512695, "identity": 0.4609452486038208, "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/vn_VOLT_reg_high/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "4a3abb92eba6b3c75c77d8789b12d4dec5c7d5603d979b651c5b2b934e5ef2e6", "generation_seconds_batch": 13.480389957898296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.58526611328125, "target_z": -1.2656250353888019, "ce": 6.316492557525635, "genuineness": 4.3881025314331055, "identity": 0.5345754623413086, "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/vn_VOLT_reg_high/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "1db66b8da29a0663ab6b054f2c4a1f7f4263ff119bf023e1866a49e9bd9acc29", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e12f48cda91396f8b91b481e323894124ee9aa3595f7ed7779072df01f583efb", "generation_seconds_batch": 19.844786196947098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7888107299804688, "target_z": -1.031249967828362, "ce": 6.229123115539551, "genuineness": 4.250029563903809, "identity": 0.48682260513305664, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1db66b8da29a0663ab6b054f2c4a1f7f4263ff119bf023e1866a49e9bd9acc29.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "1e1c863c15c3ff02d7541ae73b8101636ed5dabb20f7b2ce4fd2732b7ccad514", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9f1317921eaa3944be3efed535da74cf653259c82f0a584e74bdb135281058c9", "generation_seconds_batch": 15.623937548953108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8091652393341064, "target_z": -1.0078124061660556, "ce": 6.316492557525635, "genuineness": 4.118232727050781, "identity": 0.5233038067817688, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1e1c863c15c3ff02d7541ae73b8101636ed5dabb20f7b2ce4fd2732b7ccad514.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "1e399a1db88bb4fac6f8e3c1911de6a0ae3cd0e4fe823fd9b75815b8be88302b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bfd600182b93e27cddd999817481f1d202db7a4bf5887dd57e4b1ebf46a1ce8c", "generation_seconds_batch": 21.07562426000368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.57076096534729, "target_z": -0.13085946762750794, "ce": 6.125868320465088, "genuineness": 4.250029563903809, "identity": 0.2645139694213867, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1e399a1db88bb4fac6f8e3c1911de6a0ae3cd0e4fe823fd9b75815b8be88302b.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "576f4197a77b007c179393975a664b98b6f46c1907942de43f8f81fc5676f435", "generation_seconds_batch": 15.282993925968185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.707392930984497, "target_z": -1.1249999399462756, "ce": 6.284721851348877, "genuineness": 4.381826400756836, "identity": 0.6064794063568115, "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/vn_VOLT_reg_high/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.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": "1ebc513f9f451743c93e043f4cf75e13539441f34bc125856053a1b911237a7a", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4975c975b428ca209acaf89de528b08c62ab551832290e3a5341ff6462c64d88", "generation_seconds_batch": 13.766586395096965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.677621841430664, "target_z": -0.007812612064539292, "ce": 6.109982967376709, "genuineness": 4.2751336097717285, "identity": 0.5770547986030579, "hypothesis": "Je beri kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1ebc513f9f451743c93e043f4cf75e13539441f34bc125856053a1b911237a7a.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "1ef784b4be54b66af2d82d80ce00499bc69180f8918ac6dad02b8cf9ab7211cf", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "42cfb41c06cf8d7c7daa6b693d7b337f4c9b4f8f49099e94a49d20a358fb3adf", "generation_seconds_batch": 16.334690026007593, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5581269264221191, "target_z": -1.296874934584336, "ce": 6.197352409362793, "genuineness": 4.545003414154053, "identity": 0.6322764158248901, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/1ef784b4be54b66af2d82d80ce00499bc69180f8918ac6dad02b8cf9ab7211cf.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "20176bebdaef538af2769bf30a01f7ae84ef38d94b167de2af926176bf12a909", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "49961ed5782bcdb254f8971cb2cc523cb89c7ae96726051681e63a807772e00e", "generation_seconds_batch": 15.93534588906914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.361367106437683, "target_z": -1.5234375273458924, "ce": 6.062326908111572, "genuineness": 4.293961524963379, "identity": 0.6756009459495544, "hypothesis": "La porte 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/vn_VOLT_reg_high/20176bebdaef538af2769bf30a01f7ae84ef38d94b167de2af926176bf12a909.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "205a8e0964b8d67ffe1c3af9b1c4125619c99d78cc48ccd9267001614488783b", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3f29894616ad76da312cae2222f85ee83d51bb19cee91f43639510b13f48d9a0", "generation_seconds_batch": 16.162707755924203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2867341041564941, "target_z": -1.6093750246649225, "ce": 6.038498878479004, "genuineness": 4.193545341491699, "identity": 0.371498167514801, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/205a8e0964b8d67ffe1c3af9b1c4125619c99d78cc48ccd9267001614488783b.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "209b7bf40cf345c7ff9be5c63d6cd7eb64f33d5b02e5786fbfe4f1c2f86080b5", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1e21a79123961b28a65203fbb6e5d823d925facd1cbe62289d3e275dd55d6c19", "generation_seconds_batch": 22.342707116971724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0161020755767822, "target_z": -0.7695313071046576, "ce": 6.268836498260498, "genuineness": 4.3881025314331055, "identity": 0.6144956350326538, "hypothesis": "I find 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/vn_VOLT_reg_high/209b7bf40cf345c7ff9be5c63d6cd7eb64f33d5b02e5786fbfe4f1c2f86080b5.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "20b6d61dbf5a781190299930cd3371478a61487f40bc92ba085aa0099e3bc0d1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c1ed29398efe2f116734af8028946e85b75241958851bf452db11ea9c05550de", "generation_seconds_batch": 21.70587643701583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8770133256912231, "target_z": -0.9296875209115647, "ce": 6.213237762451172, "genuineness": 4.218649387359619, "identity": 0.5244604349136353, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/20b6d61dbf5a781190299930cd3371478a61487f40bc92ba085aa0099e3bc0d1.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "20caa985d755be20e8712442e88ea3231e6d892d234a664c542a9ab531487a3f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "785166b24e43dc7552b41dcca172d6d79adc217dbd799f38236420074a4411db", "generation_seconds_batch": 19.300972762983292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.361367106437683, "target_z": -1.5234375273458924, "ce": 6.24500846862793, "genuineness": 4.444586753845215, "identity": 0.6185996532440186, "hypothesis": "La porte 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/vn_VOLT_reg_high/20caa985d755be20e8712442e88ea3231e6d892d234a664c542a9ab531487a3f.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "21499e18367541963ce1237bde6ebda58f80b06cd9eaef0a23bc3123d1efefc5", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "56db579493472fbe757b5191949dd6380d7e59d262cd2e7f9351b2d2ea0b1a13", "generation_seconds_batch": 20.30744131805841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.071141481399536, "target_z": 0.4453125734585736, "ce": 5.601652145385742, "genuineness": 4.042920112609863, "identity": 0.6606156826019287, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/21499e18367541963ce1237bde6ebda58f80b06cd9eaef0a23bc3123d1efefc5.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "2155839f35aef6d9b9e36c20b568996f2686e35c1b842ff8b485368650fd5d42", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90abb984f5255a020237708fca937427eeca2da647caa0f8c24a9d00552a791f", "generation_seconds_batch": 14.804364953073673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6395447254180908, "target_z": -1.2031249624664222, "ce": 5.974957466125488, "genuineness": 4.457139015197754, "identity": 0.7030898332595825, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2155839f35aef6d9b9e36c20b568996f2686e35c1b842ff8b485368650fd5d42.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": "2179f0792bdf8fcadc917313a286a7e80bbd578764a220237b4cb348ee129905", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "556a0695c02c435733f83c663faef91ee8fe8c8d67aa1a81cda67b7e41bab41e", "generation_seconds_batch": 16.066876917961054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.693823218345642, "target_z": -1.1406250268096985, "ce": 6.221180438995361, "genuineness": 4.2751336097717285, "identity": 0.5993835926055908, "hypothesis": "Niemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2179f0792bdf8fcadc917313a286a7e80bbd578764a220237b4cb348ee129905.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "21eddcbf99bae50413df22bbcbe022d72f6959c6bd256c9e3faff1f86e59c011", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0a8eea0a22022ea49f2be83610fec766b277307a60c98f934e27bdfeac411a2e", "generation_seconds_batch": 20.018656234024093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3885064125061035, "target_z": -1.4921874908847026, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.5230636596679688, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/21eddcbf99bae50413df22bbcbe022d72f6959c6bd256c9e3faff1f86e59c011.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "21f0c287e4579a9b5cb6724ba11169ad1cd40bdff1dc8597cb000f6a284ce189", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c2e53dd94d8e2573fca784f4decb2a268c0a5a0880caf40d102fd4ba2863824b", "generation_seconds_batch": 15.753814158961177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6666839122772217, "target_z": -1.1718750632708883, "ce": 6.284721851348877, "genuineness": 4.68307638168335, "identity": 0.6591798067092896, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/21f0c287e4579a9b5cb6724ba11169ad1cd40bdff1dc8597cb000f6a284ce189.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "23028994c3c649989840a9ec68cc126877024ab06d5c6dab9e654c5a1b959423", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fae50ccbbc873509e6e3058dddee6f5c2e9cc27382532cd49e238b6c3a6a3162", "generation_seconds_batch": 20.80539725208655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1789379119873047, "target_z": -0.5820310883375187, "ce": 6.125868320465088, "genuineness": 4.049196243286133, "identity": 0.7730104923248291, "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/vn_VOLT_reg_high/23028994c3c649989840a9ec68cc126877024ab06d5c6dab9e654c5a1b959423.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "2329a65b1ef93ce36525950fa5707dd6f4bba1da1aeb1d741cb895f4f451cfc8", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "74292742c58ceffa0b29dc08c76e0fc8acf259c9f4ad8a544e27e15d92192f40", "generation_seconds_batch": 15.623499669949524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.195899724960327, "target_z": -0.5625001072387936, "ce": 5.855817794799805, "genuineness": 4.293961524963379, "identity": 0.647641122341156, "hypothesis": "La porte 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/vn_VOLT_reg_high/2329a65b1ef93ce36525950fa5707dd6f4bba1da1aeb1d741cb895f4f451cfc8.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "23399bb3db1956f1e38a9df83a20bac198a8401ca52e0f0e36a21f24ca7e53ac", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d717a437ecea452e7c6c79023e683d3a5c4149d0d9f4d1a70e85c2a03cbaa8c8", "generation_seconds_batch": 14.896244908100925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.191746711730957, "target_z": -1.7187499463806033, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.7002333998680115, "hypothesis": "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/vn_VOLT_reg_high/23399bb3db1956f1e38a9df83a20bac198a8401ca52e0f0e36a21f24ca7e53ac.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "23a843adb2b1b9cd54c1391d5340b855fa49a6491663cac546d38a05f525064c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5631d2306b4e11e71d33b8db192f9a736b90ae578e75f4bfb412280527070b23", "generation_seconds_batch": 15.220866663963534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9041526317596436, "target_z": -0.898437484450375, "ce": 5.462655067443848, "genuineness": 3.8797430992126465, "identity": 0.5644915699958801, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/23a843adb2b1b9cd54c1391d5340b855fa49a6491663cac546d38a05f525064c.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "23b0d532f6e4ccdced86136b664710f6063a7e85749a724f6c4fcaf8b6481e40", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1682324560ecc60528a3f173ebc63834617e5c3e6fb355d4d99decaae5446ce6", "generation_seconds_batch": 23.79584908601828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1212668418884277, "target_z": -0.648437467292168, "ce": 6.149696350097656, "genuineness": 4.118232727050781, "identity": 0.7216704487800598, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/23b0d532f6e4ccdced86136b664710f6063a7e85749a724f6c4fcaf8b6481e40.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "23bedfb89beea8cacd36ccc9167c0e5566e5771a7029b076dcc988cd4480998d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cf10efbce24200fa6679105af62335b354c0ba690b6bd3566d6e3a401a817e28", "generation_seconds_batch": 14.97009151999373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6531143188476562, "target_z": -1.1875000128686553, "ce": 6.109982967376709, "genuineness": 3.873466968536377, "identity": 0.29139983654022217, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/23bedfb89beea8cacd36ccc9167c0e5566e5771a7029b076dcc988cd4480998d.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "23e50fbc582aebc51bda467e0e8f4244ff51a3f605b20ef14c2e9aeb4e9a0c1d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e05a6569170c4e0a45ce0f5b98d5d80df8c398f2a4010487fdf97a5b280f257c", "generation_seconds_batch": 20.998227727948688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.315394878387451, "target_z": 0.7265624898123146, "ce": 5.824047088623047, "genuineness": 3.587907314300537, "identity": 0.5602797865867615, "hypothesis": "Ik 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/vn_VOLT_reg_high/23e50fbc582aebc51bda467e0e8f4244ff51a3f605b20ef14c2e9aeb4e9a0c1d.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "24042e5609964b0e1bea63856680c23235f160fe818eaeae499d94b5786639a4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "78f7bbe6368f6d311f808549c30034ead12ce53e6f958883dc562cc45769fd14", "generation_seconds_batch": 21.210604608990252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3477975130081177, "target_z": -1.5390624769436594, "ce": 5.855817794799805, "genuineness": 3.785602569580078, "identity": 0.6063607931137085, "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/vn_VOLT_reg_high/24042e5609964b0e1bea63856680c23235f160fe818eaeae499d94b5786639a4.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "24152a451b789515011621073361070dd375fb88a5e14e6b6305c077fea2b0f6", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3632e96c33da572bd5aeb11e147ac73b8b45c1356ab0319c4df0839ddac0397c", "generation_seconds_batch": 16.12294266500976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.415645718574524, "target_z": -1.4609374544235127, "ce": 6.308549880981445, "genuineness": 4.105680465698242, "identity": 0.36931338906288147, "hypothesis": "The 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/vn_VOLT_reg_high/24152a451b789515011621073361070dd375fb88a5e14e6b6305c077fea2b0f6.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "241b69cf2cb960d667a9ae3c461e361aa889ff821ac146422e0c504902219191", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ff53403644df207e4f50b28a0d6a3f3f2eb68a2a1bbd64bda167babfb16d98b2", "generation_seconds_batch": 15.11819118494168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.361367106437683, "target_z": -1.5234375273458924, "ce": 6.157639026641846, "genuineness": 4.319066047668457, "identity": 0.6152200698852539, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/241b69cf2cb960d667a9ae3c461e361aa889ff821ac146422e0c504902219191.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "242ddd778f4655c63e4916a2190b440c6478482f42e93c6fb41f23a0c57a966b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "63dfb62c88d1291cd2587ee4ff2ee16309b9209be9abf44737431c3a199956d2", "generation_seconds_batch": 20.33589414798189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7335968017578125, "target_z": 0.05664075113963095, "ce": 5.506340026855469, "genuineness": 3.8922953605651855, "identity": 0.5973573923110962, "hypothesis": "La porte 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/vn_VOLT_reg_high/242ddd778f4655c63e4916a2190b440c6478482f42e93c6fb41f23a0c57a966b.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": "250f0c13ff99f26aadf79ec0dbf2e7d49ed553dc94675dbb6812751dd47715e8", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6119df4feb707c7be38dfe141ca24018a2c5a04d18a392ceff1520323e624ba0", "generation_seconds_batch": 20.661556364037097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9982047080993652, "target_z": 0.36132822915567825, "ce": 5.982900142669678, "genuineness": 4.049196243286133, "identity": 0.5469672679901123, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos abrirlo.", "wer": 0.05, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/250f0c13ff99f26aadf79ec0dbf2e7d49ed553dc94675dbb6812751dd47715e8.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "2583e5424d59e56968e929f38539679a934786bb694272eacb65b24e47f6a20b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4529a423befbf0b7c4ecf220733707574f9a40aa0a1150e3622d1b54768d01de", "generation_seconds_batch": 14.981461432995275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0805578231811523, "target_z": -0.6953125906167805, "ce": 5.617537498474121, "genuineness": 3.898571252822876, "identity": 0.46142059564590454, "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/vn_VOLT_reg_high/2583e5424d59e56968e929f38539679a934786bb694272eacb65b24e47f6a20b.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "25bb5d0a050472fa254f070d7d28d94e7a1aa5896e4199e0f62c62d1db19fe7c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7378bb84c6d5e2a33c171aa2c342f577f1f4d314a9ffd5883d684a8ab1e14579", "generation_seconds_batch": 14.89258951798547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.097519874572754, "target_z": -0.6757813349867439, "ce": 6.1020402908325195, "genuineness": 4.406930446624756, "identity": 0.6531800031661987, "hypothesis": "De deur staat nog Elibit. Bordeur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.21052631578947367, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/25bb5d0a050472fa254f070d7d28d94e7a1aa5896e4199e0f62c62d1db19fe7c.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "25d7c2e1a433fc910edf3d3783300820f517e58fdc10d8655d160f9237a31373", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5000fa95a207c2b00787c002a7f50a51b325d6a5b5dce037d7a84db7069ed652", "generation_seconds_batch": 21.002210128004663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2094695568084717, "target_z": -0.546874883109715, "ce": 6.292664527893066, "genuineness": 4.099404335021973, "identity": 0.5594327449798584, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/25d7c2e1a433fc910edf3d3783300820f517e58fdc10d8655d160f9237a31373.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "260ea8f3725a13dc4bab28e65c7cc0b623de8fbf23951a0f00bbdd1d62712006", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "53d8c9908217d1a50ae00fd7c2b4b73424d6f0910d0658f572c5f2c22624cb53", "generation_seconds_batch": 16.062222703010775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6124054193496704, "target_z": -1.234374998927612, "ce": 6.006728172302246, "genuineness": 4.425758361816406, "identity": 0.556196391582489, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/260ea8f3725a13dc4bab28e65c7cc0b623de8fbf23951a0f00bbdd1d62712006.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "263e193464d1758fd2c077e4a9d70866dba6f5ec0ca3be3bba58c5d814eaf659", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1131559947296cd4c336301f0a2ea2d5126bda8ed3c5861ee4be6394e8c7de1f", "generation_seconds_batch": 14.677422499051318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7277473211288452, "target_z": -1.1015625155496251, "ce": 6.292664527893066, "genuineness": 4.532451152801514, "identity": 0.6624589562416077, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/263e193464d1758fd2c077e4a9d70866dba6f5ec0ca3be3bba58c5d814eaf659.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": "26756ce58f10922797c410f47db345a53db11f30e0a7995783437cfb81ddb91b", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Your message arrived after I had left.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fc69008e45e44e8b066a2639bbec316c69820b265276da708d45e705fee77083", "generation_seconds_batch": 15.19572552794125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8675968647003174, "target_z": 0.21093750589813365, "ce": 6.252951145172119, "genuineness": 3.8295347690582275, "identity": 0.6000515222549438, "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/vn_VOLT_reg_high/26756ce58f10922797c410f47db345a53db11f30e0a7995783437cfb81ddb91b.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "26addd59f4b9c1761cf3f76fd5b64a16559b590f6808601006f1444ac6e6a3e9", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c576118e33fb1a2efb005376c66599a55a83e6eeca9486a6fe263e2fd4be7ac7", "generation_seconds_batch": 20.640219485969283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.632759928703308, "target_z": -1.2109374372653057, "ce": 6.141753673553467, "genuineness": 4.381826400756836, "identity": 0.6375983357429504, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/26addd59f4b9c1761cf3f76fd5b64a16559b590f6808601006f1444ac6e6a3e9.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "d8537ca386d6babf57e9fe26abec8d84bc6a398c23a66fc32d2fbd5adfb77456", "generation_seconds_batch": 14.993324465001933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4631394147872925, "target_z": -1.4062499935656725, "ce": 6.348263263702393, "genuineness": 4.243753433227539, "identity": 0.33986780047416687, "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/vn_VOLT_reg_high/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.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": "26e7d53c0d6c956e05dc4005d6db0a442d3306700376fb967c0f94fec7535ce3", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Your message arrived after I had left.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "e8ed4b86e22e814a376428e611345176800b4cb168440bf152e5a1288aab1805", "generation_seconds_batch": 15.822629987960681, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1789379119873047, "target_z": -0.5820310883375187, "ce": 6.372091293334961, "genuineness": 3.9299514293670654, "identity": 0.32245898246765137, "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/vn_VOLT_reg_high/26e7d53c0d6c956e05dc4005d6db0a442d3306700376fb967c0f94fec7535ce3.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "27412d129dc8dec244fa599b9c7b2a0cea8ee66da233d7e904a1ced3d3322c8e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d9b716b8beb233decab78fa5dac9a5d9a781265165ee782632418b9514125a7c", "generation_seconds_batch": 15.109193707001396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5309876203536987, "target_z": -1.3281249710455256, "ce": 5.974957466125488, "genuineness": 4.469690799713135, "identity": 0.593262791633606, "hypothesis": "The Descades trouvait la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/27412d129dc8dec244fa599b9c7b2a0cea8ee66da233d7e904a1ced3d3322c8e.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "27626f6beae11cf324e50031d4b3998ccf3d02860fa6eb117d116295f84b061d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a1c1cdfa764fa56b7728aad35562ebb46df8d405982399fbdf25c8c41117bcff", "generation_seconds_batch": 22.429413801059127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.246785879135132, "target_z": -0.5039063403486836, "ce": 6.062326908111572, "genuineness": 4.174716949462891, "identity": 0.4733004868030548, "hypothesis": "La porte 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/vn_VOLT_reg_high/27626f6beae11cf324e50031d4b3998ccf3d02860fa6eb117d116295f84b061d.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "2784d80ea057a4d6a3e80f179ec82bfb365cf128d7de022b8f98cc57b0858145", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c63aade881a45ae310852b168cc0972ebdc433a6a530ef043f5c6dbcb2e2bc3f", "generation_seconds_batch": 16.12294266500976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.103543996810913, "target_z": -1.820312530563056, "ce": 6.125868320465088, "genuineness": 3.9048471450805664, "identity": 0.3859626054763794, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2784d80ea057a4d6a3e80f179ec82bfb365cf128d7de022b8f98cc57b0858145.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "27b3198ae05491e1891c641c0a9b8e0b62472ef0be808aea6a57f3620d671865", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8caa74f45081faaf73352e9ef1734b46ed979663d2b9102936fed48370b927de", "generation_seconds_batch": 19.39918376202695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8804056644439697, "target_z": -0.9257813521449508, "ce": 5.959072113037109, "genuineness": 4.306513786315918, "identity": 0.42658135294914246, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/27b3198ae05491e1891c641c0a9b8e0b62472ef0be808aea6a57f3620d671865.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": "27bf9c484d41f73496e8fd361e201028ae49ab880e6f68417b5d745b772e49a5", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8c425c18f236d1fad1838f9a84dde2994de4d3c2c8a51ff925c6807ec686597c", "generation_seconds_batch": 21.110895602963865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4510912895202637, "target_z": 0.8828125348526079, "ce": 5.661221981048584, "genuineness": 3.8169827461242676, "identity": 0.15920570492744446, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat!", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/27bf9c484d41f73496e8fd361e201028ae49ab880e6f68417b5d745b772e49a5.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "27c4815a3047650359be1b61bc8922f1a0a5ef45bde8574d81547e587c94d779", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3f2638464d2d5850981a9d10e03ed15b18741a9bfd35999d54a067cc3b3ae54a", "generation_seconds_batch": 21.190412599011324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8023803234100342, "target_z": -1.0156250182305948, "ce": 6.205295085906982, "genuineness": 4.494794845581055, "identity": 0.4446030259132385, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/27c4815a3047650359be1b61bc8922f1a0a5ef45bde8574d81547e587c94d779.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "27eb996dbddb44526a18e1af19340a3843a929a8ed1d185f236e57ace7ce59be", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3d1ec70be8e64d7681b5de8c23a48a42e04125b972084bab54e8ed7f63afb3e9", "generation_seconds_batch": 22.49146471603308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.262051820755005, "target_z": -0.48632810046912595, "ce": 6.141753673553467, "genuineness": 4.149612903594971, "identity": 0.4423781633377075, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/27eb996dbddb44526a18e1af19340a3843a929a8ed1d185f236e57ace7ce59be.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": "27f63bd82e37ce819723625133d00b1d131ee5de691665ca2e73f739d02e4540", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "a9a4a1468404a90a9dc4d59626ff2af116ca269f66b85901de119bed5e491e53", "generation_seconds_batch": 15.91223160608206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9787856340408325, "target_z": -0.8124999871313447, "ce": 6.23706579208374, "genuineness": 3.9676074981689453, "identity": 0.5440719127655029, "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/vn_VOLT_reg_high/27f63bd82e37ce819723625133d00b1d131ee5de691665ca2e73f739d02e4540.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "27ff51a91dfa7420ec2eb10ebb52ce66aa53d3112d7a1e0521cc27dd87b35ce7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "bdba3493d7b0812b98771bcf53defccbcffad1d27d8d46ac0ebfb3b19018b3f5", "generation_seconds_batch": 23.79584908601828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.009317398071289, "target_z": -0.7773436446378853, "ce": 6.054384231567383, "genuineness": 3.973883628845215, "identity": 0.6078310012817383, "hypothesis": "Ik 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/vn_VOLT_reg_high/27ff51a91dfa7420ec2eb10ebb52ce66aa53d3112d7a1e0521cc27dd87b35ce7.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "27ffb152a3e94a8c018b1558f33b36c06f27fc03626e138d96806f402b5ae985", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "81b5157a5b9e452c88b9f359c12a2db0d28c446b7b954a3ba58a01b08590d418", "generation_seconds_batch": 14.458082851022482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.284102439880371, "target_z": -0.4609375230563406, "ce": 6.125868320465088, "genuineness": 3.9676074981689453, "identity": 0.7388644218444824, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/27ffb152a3e94a8c018b1558f33b36c06f27fc03626e138d96806f402b5ae985.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "28098123f587609bdd4a095ef115e72257e5310b431df97e1b4374a3611f93fa", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "91d0df39e12ae9075e09b27e73b5b6125b8e7509f3d29740ba5dc9c388560d55", "generation_seconds_batch": 22.144355228054337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7616714239120483, "target_z": -1.0625000042895518, "ce": 5.5738525390625, "genuineness": 3.7793264389038086, "identity": 0.46711039543151855, "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/vn_VOLT_reg_high/28098123f587609bdd4a095ef115e72257e5310b431df97e1b4374a3611f93fa.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": "280ddb36db7fcd77e3cb3606a9380471d9759cc3ddc2588d5622b57e8da1e8a8", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Someone moved the little blue chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4f73e8160adc068ebb27657e56a973012113d4bfa65564466542b017c712311e", "generation_seconds_batch": 15.443227391922846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3773937225341797, "target_z": -0.353515617091139, "ce": 6.205295085906982, "genuineness": 3.8420867919921875, "identity": 0.3782477378845215, "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/vn_VOLT_reg_high/280ddb36db7fcd77e3cb3606a9380471d9759cc3ddc2588d5622b57e8da1e8a8.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "2823b9bc750de79a8460cce504b87a0ea55fc9b10607762ac4ffd083db9d7ef3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aa44399317b4ba5ccc39e8bd463a5bb7c26178a5f589c2041bd6245b84e26d70", "generation_seconds_batch": 19.36391437589191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7752411365509033, "target_z": -1.046874917426129, "ce": 6.300607204437256, "genuineness": 4.093128204345703, "identity": 0.26594477891921997, "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/vn_VOLT_reg_high/2823b9bc750de79a8460cce504b87a0ea55fc9b10607762ac4ffd083db9d7ef3.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "28572c72e16774ecc85a3b87ed6efd3362cffaa53aabb346942fefd8c0455728", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bcce3150977f682a07ff4cfe678e41747bece50514ffa943a22b488569995215", "generation_seconds_batch": 15.686770553002134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2799493074417114, "target_z": -1.617187499463806, "ce": 6.117925643920898, "genuineness": 4.149612903594971, "identity": 0.7323601245880127, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/28572c72e16774ecc85a3b87ed6efd3362cffaa53aabb346942fefd8c0455728.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "28adad98d08b620c370a4809e0ba11b615ddc3b7809d68e083094e847f0ecb84", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "bdde91c9f0497585d3f51ca023bc1647f397713c3fc238a9dab8f3e1418285de", "generation_seconds_batch": 14.698394011938944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.134836435317993, "target_z": -0.6328125176944009, "ce": 6.1894097328186035, "genuineness": 4.18099308013916, "identity": 0.5491939783096313, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/28adad98d08b620c370a4809e0ba11b615ddc3b7809d68e083094e847f0ecb84.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "29733337d5b03ff03350381613d5043c853bdbd6fbf172e70dc3fd3df7d37691", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ea3d2cf9acc5073c95171f63adb73c9d38230bd0cb10ed07f5e782db64183568", "generation_seconds_batch": 16.044967207941227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5309876203536987, "target_z": -1.3281249710455256, "ce": 6.173524379730225, "genuineness": 4.444586753845215, "identity": 0.7728399038314819, "hypothesis": "The sum proven verst.", "wer": 1.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/29733337d5b03ff03350381613d5043c853bdbd6fbf172e70dc3fd3df7d37691.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "2995375f70db2750a583be521dc49aa36a30544e5bbb3fa021eaabbf621766fa", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1dad332920c839153ef39611e505092178359167fb8e6d5d680c3021cde8df60", "generation_seconds_batch": 20.65286208607722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.273925304412842, "target_z": -0.472656166621838, "ce": 6.165581703186035, "genuineness": 4.118232727050781, "identity": 0.5623542070388794, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2995375f70db2750a583be521dc49aa36a30544e5bbb3fa021eaabbf621766fa.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "29c5ed3bc606ad1ad1324623549b3e114b7890ca766539850e29c55439933bf2", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a42c3da5681dfdff77fc586ce7ff0970599febea0720f4db4d8fcfd0cf3e5c04", "generation_seconds_batch": 21.066096176975407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6996726989746094, "target_z": 0.017578239879557624, "ce": 5.375286102294922, "genuineness": 3.798154592514038, "identity": 0.5891730189323425, "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/vn_VOLT_reg_high/29c5ed3bc606ad1ad1324623549b3e114b7890ca766539850e29c55439933bf2.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "2a4c15c6ed52ce39034b5f9814f0499e94a51cc063e88fc8407a41fc2ed52b87", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c4c9c229fcd850bf439a5116e77a85c0f3378e333263a45e54c7be1eab270ff6", "generation_seconds_batch": 16.443594383075833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6531143188476562, "target_z": -1.1875000128686553, "ce": 6.157639026641846, "genuineness": 4.218649387359619, "identity": 0.5158650279045105, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2a4c15c6ed52ce39034b5f9814f0499e94a51cc063e88fc8407a41fc2ed52b87.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": "2a8d75381d298d6bfd35fa31bd78fcb448e38b3f4a7a7ac031939b1027c4a9b6", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "8a45896460662b69b61e60fdd80cc340d20982e2b787c4fb78a3ca4b9ceb51fc", "generation_seconds_batch": 15.553710992098786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9550387859344482, "target_z": -0.839843717560265, "ce": 6.0305562019348145, "genuineness": 4.18099308013916, "identity": 0.5885177254676819, "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/vn_VOLT_reg_high/2a8d75381d298d6bfd35fa31bd78fcb448e38b3f4a7a7ac031939b1027c4a9b6.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": "2b30525ae25d7f1c91bfec5082da94d3072f83701d0049727dddacb6d95a356b", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c55c5a8229b2e0475bb15bc3a310064384207548aa0248ae93c416ea9f028cbb", "generation_seconds_batch": 13.748697534902021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7191789150238037, "target_z": 0.040039019135312846, "ce": 5.879645347595215, "genuineness": 3.8169827461242676, "identity": 0.5761896371841431, "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/vn_VOLT_reg_high/2b30525ae25d7f1c91bfec5082da94d3072f83701d0049727dddacb6d95a356b.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "2b80ac47abc840d5283beed8887adeac932e65f5757fb70f83038cdc83c6ad9e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bf13e1cd958c6b259b0eec1ba90cc8f7f0286e89c779d356cf599df9c2b417c1", "generation_seconds_batch": 28.30564015498385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.539381265640259, "target_z": -0.16699218073055117, "ce": 6.221180438995361, "genuineness": 4.099404335021973, "identity": 0.49723726511001587, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2b80ac47abc840d5283beed8887adeac932e65f5757fb70f83038cdc83c6ad9e.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "2b9239181b74429a46e97dc9025eeda77467ce0cc2f97ed7fc82e67fe72bfb05", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "b0e8be4e419813307b9d5ed0e8082276fccebad4c2616b478d00241f7604638b", "generation_seconds_batch": 21.840540231089108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9320526123046875, "target_z": 0.2851562223860106, "ce": 5.871703147888184, "genuineness": 4.049196243286133, "identity": 0.3927832245826721, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2b9239181b74429a46e97dc9025eeda77467ce0cc2f97ed7fc82e67fe72bfb05.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "2b98bec68894f13ebecc00ea3afd7cdf7d073904300328f556136ea76442a6e5", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2da4c360938682f1f5b716bdba2fb7fdfdab99448d03c3dd7fab0845687d1f34", "generation_seconds_batch": 21.8067792650545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.641066074371338, "target_z": 1.1015623782839692, "ce": 5.6254801750183105, "genuineness": 3.490628719329834, "identity": 0.17348048090934753, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2b98bec68894f13ebecc00ea3afd7cdf7d073904300328f556136ea76442a6e5.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "2bd2698cabe10a10c1802e729ee6e78870d22fa592de32c0155b86f5e5e1fc45", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e475a48953a8c76a87e0158b04211eeb4b019fcd4659a5020b99bf6c4ca712b2", "generation_seconds_batch": 21.394090145011432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2128617763519287, "target_z": -0.542968851608757, "ce": 6.1894097328186035, "genuineness": 4.545003414154053, "identity": 0.5588157773017883, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2bd2698cabe10a10c1802e729ee6e78870d22fa592de32c0155b86f5e5e1fc45.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "2c818a7f53309fc48a448c31a89c03926cb190a18cbdc54e9a54b8893c215423", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bf8a41a0130f0d0611da6c635e2a5f44b7e15b04d2312f339fd060fc233cf507", "generation_seconds_batch": 20.694394443999045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6802536249160767, "target_z": -1.1562499764074654, "ce": 5.629451274871826, "genuineness": 3.8797430992126465, "identity": 0.4623647630214691, "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/vn_VOLT_reg_high/2c818a7f53309fc48a448c31a89c03926cb190a18cbdc54e9a54b8893c215423.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": "2cdd955a7e2e53fd5159cde54fd60409e4f281d4eb36e517d5ee3633afb444a9", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "4d906a526f2b72bb256c4202bb986bcf33d117152ff466be515a9a2fc7f4404c", "generation_seconds_batch": 15.360149635002017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0194945335388184, "target_z": -0.765625001072388, "ce": 6.443574905395508, "genuineness": 4.3127899169921875, "identity": 0.45563217997550964, "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/vn_VOLT_reg_high/2cdd955a7e2e53fd5159cde54fd60409e4f281d4eb36e517d5ee3633afb444a9.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "2ce09d657771caf5ecd67320a20a54e01eba80295dcdff7c6dffe9dfdc0862d6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bc45055f2733e00fc31b8755c51c8c5c312c12ef03726ae5f52352cf80ddae3a", "generation_seconds_batch": 15.777662654989399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.005924940109253, "target_z": -0.7812499506701549, "ce": 6.133810997009277, "genuineness": 4.65797233581543, "identity": 0.683945894241333, "hypothesis": "La porte 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/vn_VOLT_reg_high/2ce09d657771caf5ecd67320a20a54e01eba80295dcdff7c6dffe9dfdc0862d6.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "2d1ad0decc2363fca52bff7a4a0670eb96de2b4edcf8c126c4f18a3886a044a2", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "74b54a3a5af0d1ca1f81249b27daace974b4362cfbabc90729fa8eed5aac3cbd", "generation_seconds_batch": 14.491837114910595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6911916732788086, "target_z": 0.007812612064539292, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.6277331113815308, "hypothesis": "La porte 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/vn_VOLT_reg_high/2d1ad0decc2363fca52bff7a4a0670eb96de2b4edcf8c126c4f18a3886a044a2.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "2d23b71213a6fde2fd5b4a01b3ab4d8fb7010c4b1b9264cd8289f38a72eec097", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5f3f0c276770835214a9546a923f631403205c3c935518eaa7d9e5fe580ea840", "generation_seconds_batch": 22.234715519007295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.374936819076538, "target_z": -1.5078124404824695, "ce": 6.141753673553467, "genuineness": 4.268857479095459, "identity": 0.6483039259910583, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2d23b71213a6fde2fd5b4a01b3ab4d8fb7010c4b1b9264cd8289f38a72eec097.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "2d7ff41f03f3dc91b6300cd7f14f0ff6e07a3e07613dfa429d2f559d3f8fba23", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "70f221777670d76613443d726b8dd5a8b6dafce47e40c7c413013b2d3831e4c3", "generation_seconds_batch": 15.547381401993334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.707392930984497, "target_z": -1.1249999399462756, "ce": 6.173524379730225, "genuineness": 4.444586753845215, "identity": 0.6773889064788818, "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/vn_VOLT_reg_high/2d7ff41f03f3dc91b6300cd7f14f0ff6e07a3e07613dfa429d2f559d3f8fba23.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "2ea6b6ad88bb6ff48851eef8860837cb48485575d9bc9d5e3c0ffcf488f96b58", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd729b6022ec046f2c07e36a5e4b3961ddb5623c9acb32f121e3d487d4290e33", "generation_seconds_batch": 20.885774613008834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4224305152893066, "target_z": -1.4531249796246293, "ce": 6.117925643920898, "genuineness": 4.400654315948486, "identity": 0.5016108751296997, "hypothesis": "La porte 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/vn_VOLT_reg_high/2ea6b6ad88bb6ff48851eef8860837cb48485575d9bc9d5e3c0ffcf488f96b58.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "2eaef854bdd6d85770b0de5409ee86b755c2d0c125a32934791035b407e23f14", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d5d0591a843b8560fbaa278b16075472b0d414c0dce74e102e1ce4d09c9ede33", "generation_seconds_batch": 15.943135960027575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2867341041564941, "target_z": -1.6093750246649225, "ce": 6.109982967376709, "genuineness": 4.281409740447998, "identity": 0.8094416856765747, "hypothesis": "La porte 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/vn_VOLT_reg_high/2eaef854bdd6d85770b0de5409ee86b755c2d0c125a32934791035b407e23f14.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "2eca052e30a543319e16c346d9b682ca6e4d25d795cb1c0dff3c13415b058a9b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "10266b162c647941227eb476b5409b06542094821f1003f782d641522fe5e6d6", "generation_seconds_batch": 15.338143707020208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.632759928703308, "target_z": -1.2109374372653057, "ce": 6.395919322967529, "genuineness": 4.174716949462891, "identity": 0.4368990659713745, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2eca052e30a543319e16c346d9b682ca6e4d25d795cb1c0dff3c13415b058a9b.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "2ed51f0855dacbe229bb4d6a48f8abf347a505b5cee78007fdd03f309a94986d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8dd84df046601796c875ff50ec60d3ce1fb7f152de5f114f292b864757469fd2", "generation_seconds_batch": 20.35242151201237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.707392930984497, "target_z": -1.1249999399462756, "ce": 5.49045467376709, "genuineness": 3.9927117824554443, "identity": 0.4039173722267151, "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/vn_VOLT_reg_high/2ed51f0855dacbe229bb4d6a48f8abf347a505b5cee78007fdd03f309a94986d.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "2f0c8faf1a02376bf64efdead775b90a18918d3ec021fc986cc54041eb69605b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "81d219ca0dfd85f060e19f11445f3ae868f492c1db993a59103ca86bd480a330", "generation_seconds_batch": 22.22014442004729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7955955266952515, "target_z": -1.0234374930294785, "ce": 6.23706579208374, "genuineness": 4.281409740447998, "identity": 0.40263456106185913, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2f0c8faf1a02376bf64efdead775b90a18918d3ec021fc986cc54041eb69605b.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "2f21bca63f305c0c769aaa2471b2fd287df9adfa2e946bcd407a1ec115dd62d6", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f41e6318ad4f8f66e3ddc0caf0fc6932a9e0fa7e0143ea1172d19ecaa0db44d9", "generation_seconds_batch": 15.845627593924291, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.149696350097656, "genuineness": 4.444586753845215, "identity": 0.7657684087753296, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2f21bca63f305c0c769aaa2471b2fd287df9adfa2e946bcd407a1ec115dd62d6.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "2f9cdec52cdeb395f0bff3dad44c09296fd07a7bad559923810d615f720ec845", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8ef99b4033ff334eac1a88ef9d1654408441868dac448d20f6cc770af9e38a92", "generation_seconds_batch": 21.166453338926658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.376458168029785, "target_z": 0.796874900267922, "ce": 5.585766792297363, "genuineness": 3.9299514293670654, "identity": 0.6342993378639221, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2f9cdec52cdeb395f0bff3dad44c09296fd07a7bad559923810d615f720ec845.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "2fb07bac160640792bb79f12cc01a8e597bd09c69590a57b6d0de2d23e635a21", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6417a0379e68203f735dfbcac9bdfcbf6ab3c37aacf5b11f6d93ecdd5953f05f", "generation_seconds_batch": 19.822016085963696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9787856340408325, "target_z": -0.8124999871313447, "ce": 6.125868320465088, "genuineness": 3.8922953605651855, "identity": 0.49445655941963196, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2fb07bac160640792bb79f12cc01a8e597bd09c69590a57b6d0de2d23e635a21.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "2fd3cc233852a4eecf1b73990785cd85b6931eb1f61d6293f03dde8eb4e0737b", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7f7222ff2edaba044ce3026c30edd11ba82258960758b04dbef0412cf9e1e0b7", "generation_seconds_batch": 15.89797498495318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.598835825920105, "target_z": -1.249999948525379, "ce": 6.340320587158203, "genuineness": 4.331617832183838, "identity": 0.5881723165512085, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/2fd3cc233852a4eecf1b73990785cd85b6931eb1f61d6293f03dde8eb4e0737b.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "2fe24e0d44c91632f0fb93efd58959dff9b4883a97b2d9f446abcc45d8cc8c00", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9cba1a2b1af0187c814648d8c4342719c81edb9d3745ed3451bccc388871d63d", "generation_seconds_batch": 16.19314716104418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.490278720855713, "target_z": -1.3749999571044826, "ce": 6.221180438995361, "genuineness": 4.369274139404297, "identity": 0.7244647741317749, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu beux prêts.", "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/vn_VOLT_reg_high/2fe24e0d44c91632f0fb93efd58959dff9b4883a97b2d9f446abcc45d8cc8c00.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "3027e6b4d5348e33999ab28f961bcb582fa7dc7ebb1ac3802bbdd46ea04f7612", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4f1fd81907fe0df254f332df119862523ac9e9ebff2373be07a79bab934290cf", "generation_seconds_batch": 21.22404270991683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.005924940109253, "target_z": -0.7812499506701549, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.7315514087677002, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3027e6b4d5348e33999ab28f961bcb582fa7dc7ebb1ac3802bbdd46ea04f7612.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "30513842436eb4aded7b1463e9b7a12e3fb5789568eaecd328129aa4f443177a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1da27276ce1548e0a85626ed84be930be472449bab9955e6d978e5dc39642aaf", "generation_seconds_batch": 21.448631189996377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3817216157913208, "target_z": -1.499999965683586, "ce": 6.435632705688477, "genuineness": 4.457139015197754, "identity": 0.37567293643951416, "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/vn_VOLT_reg_high/30513842436eb4aded7b1463e9b7a12e3fb5789568eaecd328129aa4f443177a.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "30b0e0ee1f1a3f8042ee04137c9edebb92023017f68a28b33e85ab8bf8156234", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8431d0f34b5405d73b0dc793683a06b07cd2ad7ab4855f2055f335518df7b601", "generation_seconds_batch": 16.534035066026263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1238985061645508, "target_z": -1.79687496890075, "ce": 5.9431867599487305, "genuineness": 3.9927117824554443, "identity": 0.5442938208580017, "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/vn_VOLT_reg_high/30b0e0ee1f1a3f8042ee04137c9edebb92023017f68a28b33e85ab8bf8156234.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "30b83955e022e0ddc05a7e0da335766a06557e0cbf0cb4f31ae882c180deaab7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e5a62146d1d5067d1308471d1645174f1ebb92f8385f2fae4c683e56e35e590a", "generation_seconds_batch": 21.297413734020665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.124659299850464, "target_z": -0.6445311612598983, "ce": 6.0305562019348145, "genuineness": 3.911123275756836, "identity": 0.42598479986190796, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/30b83955e022e0ddc05a7e0da335766a06557e0cbf0cb4f31ae882c180deaab7.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "310c3b7b5482d5d548d9800313b8a6db01e368236fda4bafe932fbc199f06c3c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "92d3510f57494e94f39e96426a034837552f3a3650409f7c5ce7efb4973f50ff", "generation_seconds_batch": 21.432823205017485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6870384216308594, "target_z": -1.148437501608582, "ce": 6.197352409362793, "genuineness": 4.306513786315918, "identity": 0.7611559629440308, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/310c3b7b5482d5d548d9800313b8a6db01e368236fda4bafe932fbc199f06c3c.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "31c55b35c9fca15ddb5dd7fcc2510280ac827d9208984b94e71e7e10cea9fc27", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6f32f2bd489c8d16a1fb81389afebb952645ee29919c098cab765a0acd941b84", "generation_seconds_batch": 15.450467288028449, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3817216157913208, "target_z": -1.499999965683586, "ce": 5.895530700683594, "genuineness": 4.268857479095459, "identity": 0.6392755508422852, "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/vn_VOLT_reg_high/31c55b35c9fca15ddb5dd7fcc2510280ac827d9208984b94e71e7e10cea9fc27.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "3223cf5b9655849e93bd6fd16dae4e5f3b40daaa06b6617e6dccfb400678aa9d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "023883dae8db82e90f92c0ff061e37ae427d00d31038d014f064faa4067a8d21", "generation_seconds_batch": 21.294805258046836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.609773635864258, "target_z": -0.08593763458468594, "ce": 5.804190158843994, "genuineness": 3.973883628845215, "identity": 0.5136846303939819, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3223cf5b9655849e93bd6fd16dae4e5f3b40daaa06b6617e6dccfb400678aa9d.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "324ca7435427494f2785389e0f2f8642524ad6bbfcd8eba532662e1b0a8d1c21", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "d59766007652af7db8bc1efafd27a14c729b12dbaa3fe83c8df54f1e8448500a", "generation_seconds_batch": 20.533020277041942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.673468828201294, "target_z": -1.1640624512063489, "ce": 5.629451274871826, "genuineness": 3.7542223930358887, "identity": 0.3671819865703583, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás viendo.", "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/vn_VOLT_reg_high/324ca7435427494f2785389e0f2f8642524ad6bbfcd8eba532662e1b0a8d1c21.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "328a70d0babf64a52727403d2496cd21537daa9bc563a6cb296a9459a94a30bb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04e48ee3131fe83c2875ec4d2c0850113d78e4c9e0a231c28bd1515008f3fbbd", "generation_seconds_batch": 20.43950641003903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.361367106437683, "target_z": -1.5234375273458924, "ce": 6.0305562019348145, "genuineness": 4.15588903427124, "identity": 0.6657727956771851, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/328a70d0babf64a52727403d2496cd21537daa9bc563a6cb296a9459a94a30bb.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "32c402f95db83eebddcb754796c2bbab23b19d08725ff3d423d2e933c8e7c6ea", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "984328a927ba753a11137d231c09ce1779fa13b842327d70927f76d362d417f4", "generation_seconds_batch": 19.29990041104611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8023803234100342, "target_z": -1.0156250182305948, "ce": 5.982900142669678, "genuineness": 4.281409740447998, "identity": 0.5720512270927429, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/32c402f95db83eebddcb754796c2bbab23b19d08725ff3d423d2e933c8e7c6ea.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "3337a2b3f1ded7858fd7df34b2e1a63cc1b1194b557e6ea24ba796b6b9287625", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "faa566402a82e1cdc865ac9bb7fcf6fb50fc4bcd97c900ce0fe92ac28e74d8de", "generation_seconds_batch": 22.16098135802895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.387570858001709, "target_z": -0.3417969735256416, "ce": 6.133810997009277, "genuineness": 3.823258876800537, "identity": 0.6202689409255981, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3337a2b3f1ded7858fd7df34b2e1a63cc1b1194b557e6ea24ba796b6b9287625.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "3355c8109d5ab640f303f40be4a0534741b80bdf119a34a3279e3c9ae8d74820", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e323d4519d3625ce616b6a06313de16266b2de450e24dd5d1f43416a1600fc68", "generation_seconds_batch": 19.96876279998105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3206582069396973, "target_z": -1.5703125134048492, "ce": 6.260893821716309, "genuineness": 4.519899368286133, "identity": 0.5050628781318665, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3355c8109d5ab640f303f40be4a0534741b80bdf119a34a3279e3c9ae8d74820.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "3375835f7ca264fbde9e4950c4b5203af86c1a81d01814011ee8c687272abdd3", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "686343a6485299102244cd59ca701535bbb8ce9eb9cfaff67226f334452bcc4e", "generation_seconds_batch": 16.557443215046078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5377724170684814, "target_z": -1.3203124962466422, "ce": 6.252951145172119, "genuineness": 4.011539936065674, "identity": 0.41015124320983887, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3375835f7ca264fbde9e4950c4b5203af86c1a81d01814011ee8c687272abdd3.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "33bd76ce6e8b496406f9ab29caf1fb5ff3a6a144e8f750d69e5cc05e17e070a8", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "aafe560839cb2cdf479a44a0fbed348b12fb583fa3208ad5b559473de9757ac0", "generation_seconds_batch": 21.239045281079598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3885064125061035, "target_z": -1.4921874908847026, "ce": 6.403861999511719, "genuineness": 4.3504462242126465, "identity": 0.5478830337524414, "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/vn_VOLT_reg_high/33bd76ce6e8b496406f9ab29caf1fb5ff3a6a144e8f750d69e5cc05e17e070a8.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": "33d70d69eeb9e87cb3b6a0befcfc5bae7f01c10f78ffc17260c61732a1d69def", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb76ab798f482be0d1cc36735b426ad1ce4786ff68cf89a0030c3f54e0294a14", "generation_seconds_batch": 16.358327912981622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6463295221328735, "target_z": -1.1953124876675387, "ce": 6.173524379730225, "genuineness": 4.256305694580078, "identity": 0.6633867025375366, "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/vn_VOLT_reg_high/33d70d69eeb9e87cb3b6a0befcfc5bae7f01c10f78ffc17260c61732a1d69def.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "8e2a912929eb58fa350823c8d319987bc79dea23b1bfa5ebf12badb12ac9af17", "generation_seconds_batch": 15.945109296008013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9143297672271729, "target_z": -0.8867188408848775, "ce": 6.117925643920898, "genuineness": 4.250029563903809, "identity": 0.2801641821861267, "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/vn_VOLT_reg_high/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "34641fc37d4d304f251b1e40b4927055ad6fe4c73d4c7597737890adf83c99aa", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e202229ef10a8629f8a6205a71c7a5e60240622e1b1637e05653708c22535bd0", "generation_seconds_batch": 17.961147152935155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.374936819076538, "target_z": -1.5078124404824695, "ce": 6.09409761428833, "genuineness": 4.494794845581055, "identity": 0.6276347637176514, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/34641fc37d4d304f251b1e40b4927055ad6fe4c73d4c7597737890adf83c99aa.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "346773c6f6f8f3dff4336997fcb6d1ff875d5cb852eadfa97624b63bae125ad8", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "69d9c38922edfedacd8f04cdd6a4bdf005050b89dd54a2ac3c48efba9dd4e81c", "generation_seconds_batch": 16.41749071003869, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1729137897491455, "target_z": 0.5625001072387936, "ce": 5.77639102935791, "genuineness": 3.6412534713745117, "identity": 0.35323208570480347, "hypothesis": "Ik 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/vn_VOLT_reg_high/346773c6f6f8f3dff4336997fcb6d1ff875d5cb852eadfa97624b63bae125ad8.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "6376f7d5a90f8b1ac4a0b3a7c46d678f8759bbfbc340d6d02aef42bc1ae3c12b", "generation_seconds_batch": 15.29633338097483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4224305152893066, "target_z": -1.4531249796246293, "ce": 6.403861999511719, "genuineness": 4.055472373962402, "identity": 0.17890828847885132, "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/vn_VOLT_reg_high/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "347d771963ceb5fcd97ef8fbc5c071235270eb21110a9dfd9a7e3c78e5e80558", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "faae560344bbcc4b5b0d9fecb6d438a1e29d0682a82c748eb2ba875d6af5ec69", "generation_seconds_batch": 22.37711906689219, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4995205402374268, "target_z": -0.2128905216486127, "ce": 6.078212261199951, "genuineness": 3.9173994064331055, "identity": 0.40178996324539185, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/347d771963ceb5fcd97ef8fbc5c071235270eb21110a9dfd9a7e3c78e5e80558.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "34a8d58b18337dbc49cacf296f9e000506009d31f7bab4485f691532b07ac755", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d426ea13575ed9396056f6df76895cf573e3c7a68fdc23c0a159d0329bd9a044", "generation_seconds_batch": 20.33589414798189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.7767624855041504, "target_z": 1.2578124233242627, "ce": 5.5539960861206055, "genuineness": 3.722842216491699, "identity": 0.46783962845802307, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/34a8d58b18337dbc49cacf296f9e000506009d31f7bab4485f691532b07ac755.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "34e2b90a2259c8e8b3dd09193bbbda078c4b6cff433bd45c280f0d28d4703c0f", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5871418875ffb4f9c7db542634454b29d7fc242e9e9f733e0f0bd309b86ff9ed", "generation_seconds_batch": 15.437579977093264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4088608026504517, "target_z": -1.468750066488052, "ce": 6.205295085906982, "genuineness": 4.011539936065674, "identity": 0.5685619115829468, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/34e2b90a2259c8e8b3dd09193bbbda078c4b6cff433bd45c280f0d28d4703c0f.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": "352ecfae29163d83393309fe964cabe71c73c031975b9c0a90d337eea0678843", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b16c053cad9ec249df35fa62642ad8cf6de1dda217eb1729346b4ea18445fcb7", "generation_seconds_batch": 14.078956342069432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.481710195541382, "target_z": -0.23339855968520043, "ce": 6.149696350097656, "genuineness": 4.174716949462891, "identity": 0.7374321818351746, "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/vn_VOLT_reg_high/352ecfae29163d83393309fe964cabe71c73c031975b9c0a90d337eea0678843.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "3535a7dfab840bb2a1758dccec820748d5a9f152731e8169602ee3c9c77f0796", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "96286e156ecd2604aff64ebfa4c6fc297e5d9e6b063d6669b13cf1bd290503ed", "generation_seconds_batch": 16.20551031793002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.402076005935669, "target_z": -1.4765625412869354, "ce": 5.998785495758057, "genuineness": 4.118232727050781, "identity": 0.6576117873191833, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3535a7dfab840bb2a1758dccec820748d5a9f152731e8169602ee3c9c77f0796.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "3593a33e74855e5bbeaf572f4ecfa21578981b4e572ad61dcbee55c81e554816", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "06e63ace6dc121e3f934cdcd64fb07557f0ed25f02066fddb9893154c1961416", "generation_seconds_batch": 15.029807192040607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5309876203536987, "target_z": -1.3281249710455256, "ce": 5.974957466125488, "genuineness": 4.6705241203308105, "identity": 0.6940858364105225, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3593a33e74855e5bbeaf572f4ecfa21578981b4e572ad61dcbee55c81e554816.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "35e6d65dd1cde800071d3f8e381338b76f01463bdb2626508014b9886f51f7fa", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b4f5ba92669409e52b050a1590c11fc368b609a5784e5ca5c05b6a1007302b55", "generation_seconds_batch": 21.947675788076594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8939753770828247, "target_z": -0.910156265281528, "ce": 6.046441555023193, "genuineness": 4.557555198669434, "identity": 0.5665963292121887, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/35e6d65dd1cde800071d3f8e381338b76f01463bdb2626508014b9886f51f7fa.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": "3658a1f5c22fa9d1fc5942f3dab844d9355f6d8a70531d20a2ac6eda9d893271", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "633c02eccf334ee1f85f470085f39c73807bdb11e00ffbcc67b6aab55c05c56e", "generation_seconds_batch": 14.364586618030444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.04909086227417, "target_z": 0.4199219960457882, "ce": 5.959072113037109, "genuineness": 4.068024158477783, "identity": 0.6537644863128662, "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/vn_VOLT_reg_high/3658a1f5c22fa9d1fc5942f3dab844d9355f6d8a70531d20a2ac6eda9d893271.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": "3671e2bf81a4e029c65043341643a5622795a87bb5a89648d30510de30bd884d", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "75f35c12acde2c45b580c889bf14b7101785fb6bf190887cd9de1b7a9d14175b", "generation_seconds_batch": 20.346773423952982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.519026756286621, "target_z": -0.19042974239285745, "ce": 6.3641486167907715, "genuineness": 3.9550557136535645, "identity": 0.7160604000091553, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3671e2bf81a4e029c65043341643a5622795a87bb5a89648d30510de30bd884d.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "36abe9181f02eb8cb5672ff0967342be609030d368a34707a57544b7bb7777b2", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f99b27f84860ff8af7033f436ddd8f3b813eb1ce70262e0dccbdcb3e9e7ce28e", "generation_seconds_batch": 15.214859004947357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5581269264221191, "target_z": -1.296874934584336, "ce": 6.23706579208374, "genuineness": 4.6705241203308105, "identity": 0.5359835028648376, "hypothesis": "La porte 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/vn_VOLT_reg_high/36abe9181f02eb8cb5672ff0967342be609030d368a34707a57544b7bb7777b2.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "36e7783eaa5dea0615af5e4ee0da9869c786d94f1b72e11a9ee540f1bddd9805", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 129, "seconds_generated": 10.32, "mp3_sha256": "cd83b44c4f3474206185b24cb2d5740393f7f7133a2e144741bca9f70c990407", "generation_seconds_batch": 20.105729968985543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4631394147872925, "target_z": -1.4062499935656725, "ce": 6.125868320465088, "genuineness": 4.2374773025512695, "identity": 0.6568682193756104, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/36e7783eaa5dea0615af5e4ee0da9869c786d94f1b72e11a9ee540f1bddd9805.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "36f5a4eaf72e89246934d670061c9ea02bd2fc346039daf3ebbe85544aa3cf97", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a36b86f20bc9cc05369d4b74cf4199725786c66a07a18877abe19a03fcf85c8a", "generation_seconds_batch": 15.780281141051091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6259750127792358, "target_z": -1.218750049329845, "ce": 6.157639026641846, "genuineness": 4.632867813110352, "identity": 0.5850191116333008, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/36f5a4eaf72e89246934d670061c9ea02bd2fc346039daf3ebbe85544aa3cf97.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "36fbabee73d887b89f8984416e6a87195e88749b1348902c9803c84fba2bae02", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f720d4dc0c1cc29649985f122bf9a9ffee984379e0feeb98521384960e4ddfb2", "generation_seconds_batch": 22.036047897068784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.497824192047119, "target_z": -0.2148438119304033, "ce": 5.935244083404541, "genuineness": 4.118232727050781, "identity": 0.48154765367507935, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/36fbabee73d887b89f8984416e6a87195e88749b1348902c9803c84fba2bae02.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "3726b575300375014084c723626fda4987bbf82c72fdd7efe9ab8dec28ff8791", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ec2daae09a5b0fdc4f77f6b49c2da13b830a52d0a4156aaeff2e7545d45ce606", "generation_seconds_batch": 16.06618768395856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.178176999092102, "target_z": -1.734375033244026, "ce": 6.165581703186035, "genuineness": 4.105680465698242, "identity": 0.40327006578445435, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuando estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3726b575300375014084c723626fda4987bbf82c72fdd7efe9ab8dec28ff8791.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": "37398e7fbb5e648eb4a1af12fa749c797a526c15dc62b3c9904345871bac7353", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ff0ae4c0ce8d532d63aa4818aff3e84ec82296b46db0ce98cb4c604385dd31df", "generation_seconds_batch": 13.549068054999225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3163304328918457, "target_z": -0.4238280275467463, "ce": 6.348263263702393, "genuineness": 4.042920112609863, "identity": 0.4175330698490143, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/37398e7fbb5e648eb4a1af12fa749c797a526c15dc62b3c9904345871bac7353.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "373b48e9380652324a49abe15987f564da34025f6e679b805cea9d972a7c392d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "16996e3188b29b5304c371816efbdb922f5d3527e7f552b9d71a1266603c1892", "generation_seconds_batch": 21.986977887921967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6089255809783936, "target_z": -0.08691414245992546, "ce": 6.1020402908325195, "genuineness": 3.747946262359619, "identity": 0.4633029103279114, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/373b48e9380652324a49abe15987f564da34025f6e679b805cea9d972a7c392d.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "37746a5a853b96baeeef5ccaa93db6edf9c797258bae88f2bcf59853ddc29f20", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "dd7b8e2e239720fcd9979431e6d3cc263985ee28167314104b2680710507daac", "generation_seconds_batch": 20.31556551810354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9109374284744263, "target_z": -0.8906250096514914, "ce": 6.09409761428833, "genuineness": 4.7332844734191895, "identity": 0.7294278144836426, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/37746a5a853b96baeeef5ccaa93db6edf9c797258bae88f2bcf59853ddc29f20.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "377c664b465fc434bf8c9245c8cb2191eebe8fb4f3b57039d0e283b6b9ff2443", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54f5319a597f659c34bb0eb4ac640f7255cc66f31e3f3d1f4675e894b1813cd1", "generation_seconds_batch": 15.445601391955279, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.165581703186035, "genuineness": 4.645420074462891, "identity": 0.8216441869735718, "hypothesis": "La porte 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/vn_VOLT_reg_high/377c664b465fc434bf8c9245c8cb2191eebe8fb4f3b57039d0e283b6b9ff2443.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "377d56e45578159c4ce4b7304a79dbb53648ff29577e33d9f17d408325bd3293", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a4129bec4c7b3b397bfa0c86ba608ff8ae78bbeff5bce7d86bcc2a0a18f8dbcf", "generation_seconds_batch": 20.011492097983137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.314634084701538, "target_z": -0.42578131782853695, "ce": 6.173524379730225, "genuineness": 3.9425034523010254, "identity": 0.8283422589302063, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/377d56e45578159c4ce4b7304a79dbb53648ff29577e33d9f17d408325bd3293.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "378f9985e61326fee2b9edd434fb63f3eaa3fee3909afa99934220f41a86c3ef", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fc701358311dc8f72f4165429db7ac9fdbed5475153ded1bf82839f26143836a", "generation_seconds_batch": 15.396183019969612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4427849054336548, "target_z": -1.4296875552279786, "ce": 6.038498878479004, "genuineness": 4.331617832183838, "identity": 0.5351694822311401, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/378f9985e61326fee2b9edd434fb63f3eaa3fee3909afa99934220f41a86c3ef.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "37ebedfb979c0816768f4378d0102b84f26c07b71cf29ec1c961ca4e86da5cc9", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2171f5e0e9bff9bbb107fc551032801e3c7ab37c7fee495fab99906be42de381", "generation_seconds_batch": 15.257347498089075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5038483142852783, "target_z": -1.3593750075067155, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.562778115272522, "hypothesis": "La porte 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/vn_VOLT_reg_high/37ebedfb979c0816768f4378d0102b84f26c07b71cf29ec1c961ca4e86da5cc9.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": "3830deb18cf45f3475426e3289c27170b03c07d6d04a8a59f88f220466f83b2a", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8ae3e24a0f2183590460e11c9b847838775bb8bfc20b45225031c5cc5a1968f2", "generation_seconds_batch": 21.730097285937518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8634437322616577, "target_z": -0.9453124705093318, "ce": 6.181467056274414, "genuineness": 4.017816066741943, "identity": 0.510278582572937, "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/vn_VOLT_reg_high/3830deb18cf45f3475426e3289c27170b03c07d6d04a8a59f88f220466f83b2a.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "3842cbae4f070bbce78b3c8aaa94cecfed37c2dd4b667b9f466ceacd71a6be0c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f0ecfe1b21a4e3181ecea5c86bf7dc0c529cbaef363ce35c97d7368026a504f4", "generation_seconds_batch": 20.113678629044443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3477975130081177, "target_z": -1.5390624769436594, "ce": 5.895530700683594, "genuineness": 4.042920112609863, "identity": 0.5474279522895813, "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/vn_VOLT_reg_high/3842cbae4f070bbce78b3c8aaa94cecfed37c2dd4b667b9f466ceacd71a6be0c.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "38ae6983e633399ad4eec231e4299e40bd74873d4ee7b556fac8bbe95e0b5f40", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c0f6bf30514fd08567062a78f9119a027510883d4d3c4ae66c1a18064571b921", "generation_seconds_batch": 15.191147006000392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5716965198516846, "target_z": -1.2812499849865688, "ce": 6.308549880981445, "genuineness": 4.394378662109375, "identity": 0.2652238607406616, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/38ae6983e633399ad4eec231e4299e40bd74873d4ee7b556fac8bbe95e0b5f40.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "3908ef5909b9a8aec4d9a287f1550bd7d74f84b33dfaf6afc7312901f35761cb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "49a496613ef76c89baddcabdbe0c982d52c8a6c8d45ade4e61e95febf0bc78e5", "generation_seconds_batch": 21.23021723004058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6802536249160767, "target_z": -1.1562499764074654, "ce": 6.149696350097656, "genuineness": 4.149612903594971, "identity": 0.7033308744430542, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3908ef5909b9a8aec4d9a287f1550bd7d74f84b33dfaf6afc7312901f35761cb.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "392d90b01b48bf276cab382a43e33b4c210e9304252a07ffdb985c182779ae7c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "26fc8cb8f3b839172b8987890db6049ebcac019e04aa8ff18a6e212825f8a744", "generation_seconds_batch": 14.850619941949844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6802536249160767, "target_z": -1.1562499764074654, "ce": 6.284721851348877, "genuineness": 4.469690799713135, "identity": 0.4090190529823303, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/392d90b01b48bf276cab382a43e33b4c210e9304252a07ffdb985c182779ae7c.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "398b3e906a97e8c072a7638b7457ae27ffd782794925582ab7a5fe3de8c5fbf3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "879ff668f32ea4af248e5bd308a7cdd1c56b42cd85a3fd966f5f0e48a517b810", "generation_seconds_batch": 21.617526735994034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.768456220626831, "target_z": -1.0546875294906681, "ce": 6.173524379730225, "genuineness": 4.582659721374512, "identity": 0.6489930152893066, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/398b3e906a97e8c072a7638b7457ae27ffd782794925582ab7a5fe3de8c5fbf3.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "39b1ad85f944489d514c6b739c64abefc4800037e7a252a7472414441fc55549", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "28bd70b0459d285ae345490c10c5bbb35ac4c4f00616d39ec8904992ba7e496e", "generation_seconds_batch": 21.210604608990252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7481017112731934, "target_z": -1.0781250911529745, "ce": 5.665193557739258, "genuineness": 4.093128204345703, "identity": 0.4544537365436554, "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/vn_VOLT_reg_high/39b1ad85f944489d514c6b739c64abefc4800037e7a252a7472414441fc55549.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "39c416a09ff4ecca9b386671acb8a4d76e2a20561a7a12741e8fece545ba17a8", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d755fb7fab34b34dcf8cf34cbc51ef37ff516e36bf7da5e44f31e9fba526793e", "generation_seconds_batch": 20.70558362803422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.361367106437683, "target_z": -1.5234375273458924, "ce": 6.221180438995361, "genuineness": 4.306513786315918, "identity": 0.659625768661499, "hypothesis": "La porte 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/vn_VOLT_reg_high/39c416a09ff4ecca9b386671acb8a4d76e2a20561a7a12741e8fece545ba17a8.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "39c97d906b218fb0f332fcdd8830d5dee7e1b29cc59affecf2ba2392db99076e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "72cf3ba966441502a2f6fab960eb5ac1446f7afbdcb8e23eccdd1c36a6e7755a", "generation_seconds_batch": 20.52745135407895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3621277809143066, "target_z": -0.3710938569706966, "ce": 5.8875885009765625, "genuineness": 4.099404335021973, "identity": 0.4019361138343811, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/39c97d906b218fb0f332fcdd8830d5dee7e1b29cc59affecf2ba2392db99076e.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "39dfcb5c7bba4e6537d721d95b82a881798cacc00e529ffa8acbe5fe3b9e1f41", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d5e14e98d0d82eaa5dbce7abcb14e57e7a380ea10b369f00bdb82515a422ed8d", "generation_seconds_batch": 19.36391437589191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7209625244140625, "target_z": -1.1093749903485086, "ce": 6.38003396987915, "genuineness": 4.243753433227539, "identity": 0.46720466017723083, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/39dfcb5c7bba4e6537d721d95b82a881798cacc00e529ffa8acbe5fe3b9e1f41.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "3a40f1cb1c2da221dbe4ed919d49ce66c0251eb717186531e62f22068564834f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "7b4a8148859f45f2a96231a2aba2a1af1a9bdb04cd452e110346e974cf38e4f7", "generation_seconds_batch": 22.510580510017462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1789379119873047, "target_z": -0.5820310883375187, "ce": 6.0146708488464355, "genuineness": 3.8546390533447266, "identity": 0.46906059980392456, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinfahren.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3a40f1cb1c2da221dbe4ed919d49ce66c0251eb717186531e62f22068564834f.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "3a455a0755f5aa4d35567b3cc1b2e762a43d550de48dc71bf16df950430fe828", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4440c00020698d46828a5cf0e0883c385a6872b0cb1ffca26126dc1fcff8037", "generation_seconds_batch": 20.551902545965277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.823495626449585, "target_z": 0.16015635107256296, "ce": 5.855817794799805, "genuineness": 3.653805732727051, "identity": 0.5346538424491882, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3a455a0755f5aa4d35567b3cc1b2e762a43d550de48dc71bf16df950430fe828.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "3ab36b973ba05d9e9b9c1a08687c7d2e3d5df50aea9f8cd0ae3450e75d3bbb04", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "790a8230da9f9e064a5045776fcea2ea25a86007688e8754180980e47a58c616", "generation_seconds_batch": 20.7752492739819, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.434129238128662, "target_z": 0.8632812792225713, "ce": 5.903473377227783, "genuineness": 3.4435582160949707, "identity": 0.5870890617370605, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3ab36b973ba05d9e9b9c1a08687c7d2e3d5df50aea9f8cd0ae3450e75d3bbb04.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "3b2bf6ecd3d52d9e877863cf36ae568a5241dbeec7e3f371a25e1e08ca4f45d2", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "edeabaf7af6fa7b19663f30fc0b03a2b9e24f8af6014525d53615f57f038da57", "generation_seconds_batch": 21.43309273698833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.485015392303467, "target_z": 0.9218750461126812, "ce": 5.2045183181762695, "genuineness": 3.8922953605651855, "identity": 0.43603548407554626, "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/vn_VOLT_reg_high/3b2bf6ecd3d52d9e877863cf36ae568a5241dbeec7e3f371a25e1e08ca4f45d2.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "3b4371b005c9a6b0031673ef50b9e1e34b08a70265cdd9cbd3b3daf9202fd4ef", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "46e94e52a18a66cb8a8c84c3cd42e0c79fbb9173b54dc4806f225637277eb449", "generation_seconds_batch": 21.315544163924642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3885064125061035, "target_z": -1.4921874908847026, "ce": 6.292664527893066, "genuineness": 4.306513786315918, "identity": 0.532678484916687, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3b4371b005c9a6b0031673ef50b9e1e34b08a70265cdd9cbd3b3daf9202fd4ef.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "3b48b8eef167a50c50bfeb280de3e88352747a7f258a3e6baf51fa37ccc29fa0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2d80628669c593ed85bcb6f63273138e2bba8340ab8657bb05d6c264f1ba22f2", "generation_seconds_batch": 22.247288572019897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6124054193496704, "target_z": -1.234374998927612, "ce": 6.348263263702393, "genuineness": 4.319066047668457, "identity": 0.6216694712638855, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3b48b8eef167a50c50bfeb280de3e88352747a7f258a3e6baf51fa37ccc29fa0.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "3b4e239b6264bb59dee1eca5ea95b2de00ff27d138c64464fc50783fdcf77a03", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "dc7716cd0b7496fbc3effa33a987963426053d7301c89b3b23ba50a3d542d3f6", "generation_seconds_batch": 21.176148075028323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0507869720458984, "target_z": 0.4218750117962673, "ce": 5.661221981048584, "genuineness": 3.835810661315918, "identity": 0.5606464147567749, "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/vn_VOLT_reg_high/3b4e239b6264bb59dee1eca5ea95b2de00ff27d138c64464fc50783fdcf77a03.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "3bbc313f7cb964165eb4058d5d0378d4cd96d2e4f4e9f242d73f511203741706", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "08b4114bd1a2f1646133df0cb7a4ee3f24d088b217a7dcf35d36f1bb7a5b6121", "generation_seconds_batch": 21.75205057603307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9041526317596436, "target_z": -0.898437484450375, "ce": 6.221180438995361, "genuineness": 4.18099308013916, "identity": 0.49654245376586914, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "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/vn_VOLT_reg_high/3bbc313f7cb964165eb4058d5d0378d4cd96d2e4f4e9f242d73f511203741706.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "3bf1615536b2ff818e1db8e6dfcbde5c4d094faba5d0ec0276bba7afefe47f63", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c3526b2dc2d1c2cdba69726525a689c8752b9d846badcfb0dad5d2c843e8e2a4", "generation_seconds_batch": 21.027458452037536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0228869915008545, "target_z": -0.7617186950401182, "ce": 6.324435234069824, "genuineness": 3.9299514293670654, "identity": 0.29392629861831665, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3bf1615536b2ff818e1db8e6dfcbde5c4d094faba5d0ec0276bba7afefe47f63.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "ae5e9ccbc3d3f005f325667b71851d1e1912463b4d2b66119ef8be4673679b2c", "generation_seconds_batch": 15.909355314914137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.598835825920105, "target_z": -1.249999948525379, "ce": 6.0305562019348145, "genuineness": 4.381826400756836, "identity": 0.6098395586013794, "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/vn_VOLT_reg_high/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "3c60237c6c1baa52f7c3ef0db8b7e230f3066a53b0470f6a4480e29832b313cc", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "01f1dbe93478f9be3a7654d2e4bc3064e2291d0864304b278a672c1088d97141", "generation_seconds_batch": 16.923748617060483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.490278720855713, "target_z": -1.3749999571044826, "ce": 6.427689552307129, "genuineness": 4.457139015197754, "identity": 0.4664386510848999, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3c60237c6c1baa52f7c3ef0db8b7e230f3066a53b0470f6a4480e29832b313cc.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "3c632dc2e4d7ab537f4722c1a7bf792c6983ce9cf7d83b85eec58d285ae11e9d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "edad1c987b8d9e5c4f6ed4ef2527c113671ff3b271d1cbace69fdceec5df8d11", "generation_seconds_batch": 20.40473544294946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8804056644439697, "target_z": -0.9257813521449508, "ce": 6.252951145172119, "genuineness": 4.168440818786621, "identity": 0.5523455142974854, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschneiden.", "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/vn_VOLT_reg_high/3c632dc2e4d7ab537f4722c1a7bf792c6983ce9cf7d83b85eec58d285ae11e9d.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "3c8e18734351c0349f38e9e79cb68057c352b2ffc377bb6c10ce33eb4151bad0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ade9199334a8a26bb155d1b68284fd9bab155fe2cf6d6335651ed5818426db35", "generation_seconds_batch": 14.762510615051724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8091652393341064, "target_z": -1.0078124061660556, "ce": 6.006728172302246, "genuineness": 4.406930446624756, "identity": 0.6548187136650085, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3c8e18734351c0349f38e9e79cb68057c352b2ffc377bb6c10ce33eb4151bad0.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "3ca478b99f5be9f906a424e6391a191a0aa87681612075f1a56ef1e5efc6cafe", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6d7a5893e8a7f462e170a8ec6b75ccc3f74a080c43a414d22c1f2bf52621786c", "generation_seconds_batch": 21.117394782952033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0473945140838623, "target_z": 0.41796870576399764, "ce": 5.982900142669678, "genuineness": 3.8420867919921875, "identity": 0.5581872463226318, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3ca478b99f5be9f906a424e6391a191a0aa87681612075f1a56ef1e5efc6cafe.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "3cd79335ddd8230fa8910ff5651a9d1d672849e5979e4db139fd20248d1eb217", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c3bb44053613f01271907515e04b625f02a855d2a2d3fc8a6ec6fd2a6f772b29", "generation_seconds_batch": 22.60227452800609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4631394147872925, "target_z": -1.4062499935656725, "ce": 6.062326908111572, "genuineness": 4.406930446624756, "identity": 0.5400741100311279, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3cd79335ddd8230fa8910ff5651a9d1d672849e5979e4db139fd20248d1eb217.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "3d1ce3f95384b8779c70e1266d7ce2ac3d681f455e4eef179152ff7c39a54299", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "13331530c0ef8458b12fed5540320957d795b73bad2744da9708082755691351", "generation_seconds_batch": 21.30428825400304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5571913719177246, "target_z": -0.14648441722527497, "ce": 5.935244083404541, "genuineness": 4.300237655639648, "identity": 0.5623329281806946, "hypothesis": "La porte 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/vn_VOLT_reg_high/3d1ce3f95384b8779c70e1266d7ce2ac3d681f455e4eef179152ff7c39a54299.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "3d47d50495494ef64452d3df5a495d8d41bac6b5bc72a0de3eb24f761a1ccf94", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a883f0c113a871106568414ac8d2868a2992d78e99484c58280bd2acd3358eb9", "generation_seconds_batch": 20.370200339937583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4706850051879883, "target_z": -0.24609371112593734, "ce": 6.078212261199951, "genuineness": 3.7793264389038086, "identity": 0.7627928853034973, "hypothesis": "Ik 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/vn_VOLT_reg_high/3d47d50495494ef64452d3df5a495d8d41bac6b5bc72a0de3eb24f761a1ccf94.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": "3d74edaf30e4e7d6d92a2bb42c85ce1abdf11af72b2392b86079b274f34ff7ba", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Someone moved the little blue chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9d31c9c21d4884d4358e0c2e042ca63b5ba867c92e9ca9784487079b78f5605", "generation_seconds_batch": 22.350776192964986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4435458183288574, "target_z": -0.27734361032147137, "ce": 6.109982967376709, "genuineness": 3.886019229888916, "identity": 0.46866375207901, "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/vn_VOLT_reg_high/3d74edaf30e4e7d6d92a2bb42c85ce1abdf11af72b2392b86079b274f34ff7ba.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": "3dbfee5a1b94d3e4562285ea173fa565928a4794da3253304046738966672065", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "4fc0b989bbc637bdc6bd2e4e8a8e421b78c0da0610a2a4a0d515998afac89de4", "generation_seconds_batch": 15.812409925973043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.272228956222534, "target_z": -0.4746094569036286, "ce": 5.645336627960205, "genuineness": 4.030367851257324, "identity": 0.6086593866348267, "hypothesis": "Las llaves están en la mesa de la cocina. Mira 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/vn_VOLT_reg_high/3dbfee5a1b94d3e4562285ea173fa565928a4794da3253304046738966672065.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "3e8844237d2b54b3e9851923f43d36b618a86599e2ab7132ac6b11466fc8ae67", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b6863ffe5878870a657178b7000db2c26e516861f65db067e8552ea4f1cd32c9", "generation_seconds_batch": 20.489748116931878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6056206226348877, "target_z": -1.2421874737264955, "ce": 6.419747352600098, "genuineness": 4.369274139404297, "identity": 0.4945772886276245, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/3e8844237d2b54b3e9851923f43d36b618a86599e2ab7132ac6b11466fc8ae67.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "3ebcdd053be70115e246ec83b10e82e7b3ca920dd62371f4a43b32289d28152e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ad8233fb7263ae743933cc70feb3cbc06aaf700041f66b4a93cc5d3b99d6f275", "generation_seconds_batch": 15.777662654989399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.415645718574524, "target_z": -1.4609374544235127, "ce": 6.09409761428833, "genuineness": 4.381826400756836, "identity": 0.5771746039390564, "hypothesis": "La porte 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/vn_VOLT_reg_high/3ebcdd053be70115e246ec83b10e82e7b3ca920dd62371f4a43b32289d28152e.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": "400559bcb12aa4bfee844d155ff5de79367b64c9cf80b0a71fca2764eb25eeb7", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "04deb006235e793ea80ec191c497007903ac28f0fd1fc8bb8538a15133954cd1", "generation_seconds_batch": 15.164854426984675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8973677158355713, "target_z": -0.9062500965149142, "ce": 6.38797664642334, "genuineness": 4.419482707977295, "identity": 0.6909741759300232, "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/vn_VOLT_reg_high/400559bcb12aa4bfee844d155ff5de79367b64c9cf80b0a71fca2764eb25eeb7.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "4047ce29cbdd5d1a4ff4e1fa0ed0f7e726ac9a2a7e2b131ea23621d6dd60e260", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "64b3cc99e30f81ad9e6c6e5e5f5ff7f022d7f830a522209bab28c03dd42999b0", "generation_seconds_batch": 15.384285224950872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.693823218345642, "target_z": -1.1406250268096985, "ce": 6.41180419921875, "genuineness": 4.193545341491699, "identity": 0.37709254026412964, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.125, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4047ce29cbdd5d1a4ff4e1fa0ed0f7e726ac9a2a7e2b131ea23621d6dd60e260.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "408ed778723ff2d96c88a31540e7d7bfda18c24c01fce970cf6b513c8ea187b9", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b57bea0dc0f4305294d45a5f8a2752c04e34a555953fccbbfcc8ad0a1e3b37f0", "generation_seconds_batch": 21.613544160034508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7616714239120483, "target_z": -1.0625000042895518, "ce": 6.205295085906982, "genuineness": 3.9801597595214844, "identity": 0.26867249608039856, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/408ed778723ff2d96c88a31540e7d7bfda18c24c01fce970cf6b513c8ea187b9.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "40d7b52328b5ff8319f2d802885edbd7ba92925c02240c9a44c5e436468847c0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f3881ffd91e78fcc6a402110a2285211843800cf829517845c47da312b2d5282", "generation_seconds_batch": 22.055210676044226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.573305368423462, "target_z": -0.12792966947047782, "ce": 6.165581703186035, "genuineness": 3.9927117824554443, "identity": 0.7744441032409668, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/40d7b52328b5ff8319f2d802885edbd7ba92925c02240c9a44c5e436468847c0.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "40d8544eafdaf165496af4dc0617d1bb42cb68c460791a89ab39b2b980aec28d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9d2d8cf4e8da185da89751d691a1c8940c0184cfcc367ddf2a1192283c6940e0", "generation_seconds_batch": 19.844786196947098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8329119682312012, "target_z": -0.9804688130027912, "ce": 6.1020402908325195, "genuineness": 4.149612903594971, "identity": 0.5373115539550781, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/40d8544eafdaf165496af4dc0617d1bb42cb68c460791a89ab39b2b980aec28d.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": "41128496c82f147446a9d85c3e0fe13c5b83e0ac621ffffeed5fdf5bffe1a032", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f6954c634f33b5bf068e0b303449a6431e305cf9470bed44144716a4c7bba904", "generation_seconds_batch": 17.59566766198259, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8091652393341064, "target_z": -1.0078124061660556, "ce": 6.165581703186035, "genuineness": 3.961331605911255, "identity": 0.3696438670158386, "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/vn_VOLT_reg_high/41128496c82f147446a9d85c3e0fe13c5b83e0ac621ffffeed5fdf5bffe1a032.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "41b829718b1c4dfabbd92dc6bc076525f830e14ac77d4ae0f3a62c37ad53f46d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 132, "seconds_generated": 10.56, "mp3_sha256": "85cb96b1e14ded4480cb6edcb5f361c0042cdb8f8c249ce12e20de0f6c961851", "generation_seconds_batch": 21.880549073102884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0236477851867676, "target_z": 0.39062511260073324, "ce": 4.966238498687744, "genuineness": 3.6412534713745117, "identity": 0.6316801309585571, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "duration_error_s": 0.3600000000000012, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/41b829718b1c4dfabbd92dc6bc076525f830e14ac77d4ae0f3a62c37ad53f46d.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "4209436e8759fb8d48b03713f927934caf90e1c30d75d3d821f566d8b60c36a9", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "093122ae9da16890298e9ce2ddb540969f2841c06390f9d1f0323e2a0e7460a9", "generation_seconds_batch": 17.35800002096221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8939753770828247, "target_z": -0.910156265281528, "ce": 6.117925643920898, "genuineness": 4.105680465698242, "identity": 0.6163861751556396, "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/vn_VOLT_reg_high/4209436e8759fb8d48b03713f927934caf90e1c30d75d3d821f566d8b60c36a9.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": "424eae5ef184da358f769195f0c8ae111ba1cc375c34a97550d397f2fe3e5609", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "89181aff1c70ba117c2f4b3dc7d063bcaafb8e3dcb570fd3fe74712dfb0a68af", "generation_seconds_batch": 15.91223160608206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0839502811431885, "target_z": -0.6914062845845109, "ce": 6.133810997009277, "genuineness": 4.419482707977295, "identity": 0.45316416025161743, "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/vn_VOLT_reg_high/424eae5ef184da358f769195f0c8ae111ba1cc375c34a97550d397f2fe3e5609.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "42536c9de55e655371d23297e4507b6c4b7caee4d1ceeb24ba71bc25f8cf8a78", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f54e9cfb79a38c2d7d8750515eb054947f2a3669d48633bb2c0f430a70f1cf1f", "generation_seconds_batch": 21.43309273698833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6538751125335693, "target_z": -0.03515620522780368, "ce": 5.5659098625183105, "genuineness": 3.8169827461242676, "identity": 0.5919747352600098, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lindo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/42536c9de55e655371d23297e4507b6c4b7caee4d1ceeb24ba71bc25f8cf8a78.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "425f61503120b3a969639145cbd85bbd60d45f80ac3c6dc9ef2bf4f68396fbc9", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2bb4185a62caec835c1d3b3a16c2df91c0c3d528473d90e104be9399ed6a5d76", "generation_seconds_batch": 16.300116671947762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.707392930984497, "target_z": -1.1249999399462756, "ce": 6.300607204437256, "genuineness": 4.344170093536377, "identity": 0.4328157603740692, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/425f61503120b3a969639145cbd85bbd60d45f80ac3c6dc9ef2bf4f68396fbc9.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "42940630f6d48111488689e08e526779bb882be2e1c85beaef4734d5ceaba748", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e29f108408756dc2bc02ddc2438504b83e219111cf681ec74e683417e633212b", "generation_seconds_batch": 15.23469007993117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6301281452178955, "target_z": -0.06250007292237963, "ce": 6.229123115539551, "genuineness": 4.20609712600708, "identity": 0.5150091052055359, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/42940630f6d48111488689e08e526779bb882be2e1c85beaef4734d5ceaba748.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "429a81bb5913b685ab10ed7abe3c9b32eee8e8dfee4aa4564bee5ba7b14899c8", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "03c48015353e4c0ad67218a1409a04d5a82b9cce5fd6c548d1d2de13a3656008", "generation_seconds_batch": 15.567576886969618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.32744300365448, "target_z": -1.5625000386059658, "ce": 6.070269584655762, "genuineness": 4.168440818786621, "identity": 0.7042213678359985, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/429a81bb5913b685ab10ed7abe3c9b32eee8e8dfee4aa4564bee5ba7b14899c8.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "42ae097a0ec3e3bc7d87d233d2cda882eefadc3ffa08c1fdb04cd5ceef5695c8", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0e1d67a016f6ae8dc7427cc70c1f97861dc9feb226879a582527eb6fededb1c0", "generation_seconds_batch": 19.48051356105134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9720008373260498, "target_z": -0.8203124619302283, "ce": 6.165581703186035, "genuineness": 4.093128204345703, "identity": 0.6234925985336304, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/42ae097a0ec3e3bc7d87d233d2cda882eefadc3ffa08c1fdb04cd5ceef5695c8.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "42dda6df71bc08878145868247614163574cb04fb757406c940557eab373df71", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6bcf020984e8391e0c1f13dda9ceccb6109b6be1a07689c4e5d1aa5295e4afa5", "generation_seconds_batch": 21.465773788979277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.173524379730225, "genuineness": 4.419482707977295, "identity": 0.7035189867019653, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/42dda6df71bc08878145868247614163574cb04fb757406c940557eab373df71.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "434e8e82ad96e846650246e7cc2b199018de45d7c564b7309442eae8ca17f07b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4c4fcaee89ea4e19453444baa2036b02ac1c25859a96f6b516e88bca7d918865", "generation_seconds_batch": 22.612461411044933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.124659299850464, "target_z": -0.6445311612598983, "ce": 6.109982967376709, "genuineness": 4.086852550506592, "identity": 0.30036473274230957, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/434e8e82ad96e846650246e7cc2b199018de45d7c564b7309442eae8ca17f07b.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "4df6070ede4102832efbf5a76830c5099a6f731a91995a2117c2da827a8eef2e", "generation_seconds_batch": 15.945109296008013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.856658935546875, "target_z": -0.9531249453082152, "ce": 6.070269584655762, "genuineness": 4.243753433227539, "identity": 0.7042108774185181, "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/vn_VOLT_reg_high/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "24455a324d62adff50ff683c94d4767089d0a4997e482d118d3bda41dc254bd0", "generation_seconds_batch": 15.324904061038978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.826127290725708, "target_z": -0.988281150536019, "ce": 6.316492557525635, "genuineness": 4.356721878051758, "identity": 0.43943318724632263, "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/vn_VOLT_reg_high/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "43e1c35dffdb57d6816590cc93308ff81f5e8d0fd3b8d0246fdeb4bd6acdd872", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e80e4d84ba3bd6cd6c0ac01193542918d683a4a2a603e4c3cb78bd3c26e63448", "generation_seconds_batch": 15.576814447063953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4427849054336548, "target_z": -1.4296875552279786, "ce": 6.459460258483887, "genuineness": 4.344170093536377, "identity": 0.5378269553184509, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/43e1c35dffdb57d6816590cc93308ff81f5e8d0fd3b8d0246fdeb4bd6acdd872.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "43e442fb6be1630d3d0a9164e3189b222f494fe7cefec1673f13867b40796334", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "68780ed936be1623ccb5453ac315491f2b7c459711670a6261cfea263e9c2588", "generation_seconds_batch": 15.908425524947233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3003038167953491, "target_z": -1.5937499378014996, "ce": 6.4515180587768555, "genuineness": 4.168440818786621, "identity": 0.5337114930152893, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/43e442fb6be1630d3d0a9164e3189b222f494fe7cefec1673f13867b40796334.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "43e460db1f9049886d73d0fa3411b1b8dbdf85bb5dc603da4a9d052090df373c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65907dbbf7a6d6a404d7caa503d580641e8a218014c46aa38a1193a2002c5c57", "generation_seconds_batch": 16.03875931398943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.631824493408203, "target_z": -0.06054678264058903, "ce": 5.847874641418457, "genuineness": 3.6789097785949707, "identity": 0.48017895221710205, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/43e460db1f9049886d73d0fa3411b1b8dbdf85bb5dc603da4a9d052090df373c.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "4441e368d9ba29be69fdeda3a6260bf1ebe3fa9a76cd8e510a6fc0493f178832", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97574d1715016a862fe328763f75d69c71d69f92a2face5dbd01e1509c8d7611", "generation_seconds_batch": 16.08103142597247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3010644912719727, "target_z": -0.44140626742630396, "ce": 5.478540420532227, "genuineness": 4.055472373962402, "identity": 0.5065535306930542, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4441e368d9ba29be69fdeda3a6260bf1ebe3fa9a76cd8e510a6fc0493f178832.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "4471270476b89fc8310e8462d646fdc6712ea5e167b3fcca4f8985b6321335a9", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fdb83520940c9c9deeb4a3db0aa6025beecc8e57264a633ea0f2497beb625b46", "generation_seconds_batch": 15.382348119048402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.218885898590088, "target_z": -1.6875000471850692, "ce": 6.078212261199951, "genuineness": 4.017816066741943, "identity": 0.2628205418586731, "hypothesis": "The door is still open. I'd put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4471270476b89fc8310e8462d646fdc6712ea5e167b3fcca4f8985b6321335a9.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "44ae3e47d81bc242357e894f010c57913466cce0340e2d7d2d88093dba34d37f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a9b1eae86153c8c41af3bb6e222de5bae30e7073ee7b3a5087cbd0f2f7815f62", "generation_seconds_batch": 21.70587643701583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8091652393341064, "target_z": -1.0078124061660556, "ce": 6.348263263702393, "genuineness": 4.231201171875, "identity": 0.4103483557701111, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/44ae3e47d81bc242357e894f010c57913466cce0340e2d7d2d88093dba34d37f.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "44b154794e58d10ba818956ab1cb617a827ed8885455e6ddb0082c44b583517f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7d093bddc47f08b2095a1392fc932a8974e14ce6a3693f8f36a3c42950c843f0", "generation_seconds_batch": 17.11846595897805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7820258140563965, "target_z": -1.0390625798929012, "ce": 6.062326908111572, "genuineness": 4.406930446624756, "identity": 0.5153704881668091, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/44b154794e58d10ba818956ab1cb617a827ed8885455e6ddb0082c44b583517f.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "4505e93e04bf55f766317dbbda07f767e774047e337ef9ac298f74ccd4150543", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6247c80833c8fed1ac896849ed335deffc00da59ba5b1bf768411b50e65d74f0", "generation_seconds_batch": 21.613544160034508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.32744300365448, "target_z": -1.5625000386059658, "ce": 6.213237762451172, "genuineness": 3.9048471450805664, "identity": 0.27609983086586, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4505e93e04bf55f766317dbbda07f767e774047e337ef9ac298f74ccd4150543.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "45417300886d5a4dd16d58ff5788a1793a9a2919eeff2df72353554067008653", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "14e98ad4c039415ff182895986ca42ddd5abb50159d38f6f1f0d1f082be9b12c", "generation_seconds_batch": 15.08631440391764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8600512742996216, "target_z": -0.9492187765416014, "ce": 6.316492557525635, "genuineness": 4.319066047668457, "identity": 0.3849925994873047, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/45417300886d5a4dd16d58ff5788a1793a9a2919eeff2df72353554067008653.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "458d81c0f43bb8a899341bb481022c02b71b176680ab33da1799cfcc8bbd5700", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "13fa756150485f9ee4ba29cf58ab2825897f5c5415b67ee687129ee6d3168b14", "generation_seconds_batch": 15.712529059965163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.246785879135132, "target_z": -0.5039063403486836, "ce": 6.133810997009277, "genuineness": 4.124508857727051, "identity": 0.5052050948143005, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/458d81c0f43bb8a899341bb481022c02b71b176680ab33da1799cfcc8bbd5700.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "459ada47c0454e429cf5d6b26c8ab0e25ab2c8b90ba4c2027f09f834ee161234", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "55ee781280585de8f73b4b29b50a3f46d0c26fbc8d2c56c80bb50843d0ba66f5", "generation_seconds_batch": 20.207972623058595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4224305152893066, "target_z": -1.4531249796246293, "ce": 6.1894097328186035, "genuineness": 4.105680465698242, "identity": 0.2870294451713562, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/459ada47c0454e429cf5d6b26c8ab0e25ab2c8b90ba4c2027f09f834ee161234.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "45d8839cdcead0000c3fa81b9ad9293e9c87b591b58a5ec195798356a5203083", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f38ba9ea5d4327d09754c15d363fb63bf0d8f98487a703c4655bcd13585da37b", "generation_seconds_batch": 20.51522768905852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0805578231811523, "target_z": -0.6953125906167805, "ce": 6.022613525390625, "genuineness": 4.137060642242432, "identity": 0.6729356050491333, "hypothesis": "La porte 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/vn_VOLT_reg_high/45d8839cdcead0000c3fa81b9ad9293e9c87b591b58a5ec195798356a5203083.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "a8c0f71d33af404f7911f99e7ee184a9e21b38f650e4ff7a0562f6a500227ca6", "generation_seconds_batch": 15.321507205022499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5038483142852783, "target_z": -1.3593750075067155, "ce": 6.459460258483887, "genuineness": 4.061748504638672, "identity": 0.5630224943161011, "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/vn_VOLT_reg_high/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "45fdb94da25d33a7ad53dd613dc88b69f65a04be15a966a34a0c622a23498b67", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9cdec5fba2283593edc33d955d57ca240063550e50eb119863c08478ee8f2db8", "generation_seconds_batch": 15.861268915003166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5377724170684814, "target_z": -1.3203124962466422, "ce": 6.395919322967529, "genuineness": 4.13078498840332, "identity": 0.5360268354415894, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/45fdb94da25d33a7ad53dd613dc88b69f65a04be15a966a34a0c622a23498b67.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "46709b2c8471e4ac48d32519cd80b37d1af96d65743455ca0e982a4d04e81b33", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "51207a428858aa7ff3c5c7137833f430a3ebf4ab011914b4afa4843544764405", "generation_seconds_batch": 23.80443933303468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.350254535675049, "target_z": -0.384765516286673, "ce": 6.086154937744141, "genuineness": 4.168440818786621, "identity": 0.646677553653717, "hypothesis": "De deur 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/vn_VOLT_reg_high/46709b2c8471e4ac48d32519cd80b37d1af96d65743455ca0e982a4d04e81b33.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "46c16c156c0bc3938e0e08c2ffa1a82be1a5b397dd074c6608b687f51983bb5c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "164a1a7d45d0e2883149b9a07697ba598013d8f14defb37d3bcb6efa82118751", "generation_seconds_batch": 16.57208705402445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.942229747772217, "target_z": 0.296874865951508, "ce": 5.39911413192749, "genuineness": 3.923675537109375, "identity": 0.4109382927417755, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regard what.", "wer": 0.3684210526315789, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/46c16c156c0bc3938e0e08c2ffa1a82be1a5b397dd074c6608b687f51983bb5c.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "46d23a18b07a70827a2c236cbff233158c48da8dc20b7387ebeb513638b263b2", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1beb02c0beadbe86725d61478e59021e79d4a6cea26276640f63d170dee5afdc", "generation_seconds_batch": 21.88208942406345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.341012716293335, "target_z": -1.5468749517425429, "ce": 5.780362129211426, "genuineness": 3.8420867919921875, "identity": 0.4602643549442291, "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/vn_VOLT_reg_high/46d23a18b07a70827a2c236cbff233158c48da8dc20b7387ebeb513638b263b2.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "46d4b80d0e04e6dd718699c4a463a4da86b0fd4e0b661970251c1d813038c513", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "281041e721d07281cb0a4ea109331fc44d44c78de355d86037338dc346c05bd5", "generation_seconds_batch": 16.631165848928504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6666839122772217, "target_z": -1.1718750632708883, "ce": 6.181467056274414, "genuineness": 4.306513786315918, "identity": 0.684187114238739, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/46d4b80d0e04e6dd718699c4a463a4da86b0fd4e0b661970251c1d813038c513.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "477145f9c02da98bd9e5632e5e4ac4f15c259289a4f91d8ac7030037a1ec8033", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a3afc5e6d6222de5448a63775d44c74a1c5bcb7287e3a57fd6c914d31bee150a", "generation_seconds_batch": 15.273370073991828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6802536249160767, "target_z": -1.1562499764074654, "ce": 6.268836498260498, "genuineness": 4.557555198669434, "identity": 0.7538900375366211, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/477145f9c02da98bd9e5632e5e4ac4f15c259289a4f91d8ac7030037a1ec8033.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "47c2478be2e0eb228c51ee759f1e79c23896180153d108956940129342e23a0d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2b53035497026c6857fcd756553c49c9fdf2f2144a782aa72d8467d8537e5b93", "generation_seconds_batch": 21.407817402970977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0262794494628906, "target_z": -0.7578123890078486, "ce": 6.197352409362793, "genuineness": 4.15588903427124, "identity": 0.3511929214000702, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/47c2478be2e0eb228c51ee759f1e79c23896180153d108956940129342e23a0d.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "e3fcda8e8225f5f9fc92206b08b99a5a10821c5b2a015528b472ba86a13e5530", "generation_seconds_batch": 16.259736391948536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.598835825920105, "target_z": -1.249999948525379, "ce": 6.181467056274414, "genuineness": 4.557555198669434, "identity": 0.6582700610160828, "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/vn_VOLT_reg_high/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "47e4d2afdfa1754fbc6bff54d2e09c91a18a9519fc8e38bc344ca779365f0099", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9c9b37ed10426a9fbdcc2afc19f08751f47ec05051ce1e500996d63bbfdbb39a", "generation_seconds_batch": 19.87495442200452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2324556112289429, "target_z": -1.6718749603216463, "ce": 6.252951145172119, "genuineness": 4.406930446624756, "identity": 0.5379509925842285, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/47e4d2afdfa1754fbc6bff54d2e09c91a18a9519fc8e38bc344ca779365f0099.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "47e64fe6051e3dc8490af01678f197facb6e6f63e7d6a031fca11b10345cc23c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "619d52e1e17ccc300a729c4d20226116e7c6095eceddfe791e3bcf9c9e00c014", "generation_seconds_batch": 15.109193707001396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7888107299804688, "target_z": -1.031249967828362, "ce": 6.1020402908325195, "genuineness": 4.632867813110352, "identity": 0.7475730180740356, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what it contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/47e64fe6051e3dc8490af01678f197facb6e6f63e7d6a031fca11b10345cc23c.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": "488ceec6e1a182fafc08c87b8f542726498e8fc2f0b44c42eb888bdcf84d243b", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Your message arrived after I had left.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "fe285571cc4f7174e4fed3e1b315efbb98e6ab56defc125c007c5ff7cd325452", "generation_seconds_batch": 15.822629987960681, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063595771789551, "target_z": -0.7148438462468173, "ce": 6.324435234069824, "genuineness": 3.798154592514038, "identity": 0.47349920868873596, "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/vn_VOLT_reg_high/488ceec6e1a182fafc08c87b8f542726498e8fc2f0b44c42eb888bdcf84d243b.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": "48b806ef842515443e512225413caf76dc037f564f9c9ec200e1fb33e5c2f8e5", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The keys are on the kitchen table.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f52c37fa0a2ffb36feda4dc3c351c487d88a49ba5a8bba81f300b79d83d43869", "generation_seconds_batch": 23.53854424401652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4401533603668213, "target_z": -0.281249916353741, "ce": 6.078212261199951, "genuineness": 3.961331605911255, "identity": 0.6239593029022217, "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/vn_VOLT_reg_high/48b806ef842515443e512225413caf76dc037f564f9c9ec200e1fb33e5c2f8e5.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "49033eb4fb42b058908f215a2bdb013313d42b99b00ccbd5c86ac2c81e0da733", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ad14ee7f77f537ab216b40f0f8794e40b45f72b13192cbbd285e4d8b5d6b6449", "generation_seconds_batch": 15.220866663963534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4224305152893066, "target_z": -1.4531249796246293, "ce": 5.879645347595215, "genuineness": 3.886019229888916, "identity": 0.3503687083721161, "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/vn_VOLT_reg_high/49033eb4fb42b058908f215a2bdb013313d42b99b00ccbd5c86ac2c81e0da733.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "4903eb6af2e06e8caa94a02d5f0cf8551b8b533bfc4c2409e71fabf41e8dfd41", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f256d35af1868530fdc24e39561fed429b03178127ea9a2cbc9c1fffef1028dd", "generation_seconds_batch": 16.446868072031066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6191902160644531, "target_z": -1.2265625241287286, "ce": 6.054384231567383, "genuineness": 4.143336772918701, "identity": 0.5277383327484131, "hypothesis": "La porte 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/vn_VOLT_reg_high/4903eb6af2e06e8caa94a02d5f0cf8551b8b533bfc4c2409e71fabf41e8dfd41.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "497ca6d63d9846593fc6d35b8b5df2805f66c758a457bac486713d5d6a0b567a", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2608bea8c72e88319f237f61e0f1c4078401d91e39a26caef494201a69992423", "generation_seconds_batch": 16.443594383075833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8702285289764404, "target_z": -0.9374999957104483, "ce": 6.419747352600098, "genuineness": 4.432034492492676, "identity": 0.3839975595474243, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/497ca6d63d9846593fc6d35b8b5df2805f66c758a457bac486713d5d6a0b567a.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "e134fb13172f62e2e76d653704d77f43455633574fc9f5a2940544521414a208", "generation_seconds_batch": 15.720845017000102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5581269264221191, "target_z": -1.296874934584336, "ce": 6.205295085906982, "genuineness": 4.394378662109375, "identity": 0.5823430418968201, "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/vn_VOLT_reg_high/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "4a888ce2eb604eb7e53e68a2be530b0b6263f2efe34e7d87bc59f4199734d68f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a7ea75e9a542d89ab03a5ab7edf11c2f9e79b0eb56bca2a4a8728634985aa9aa", "generation_seconds_batch": 19.852179751032963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.418102741241455, "target_z": -0.30664049376652636, "ce": 6.117925643920898, "genuineness": 4.017816066741943, "identity": 0.3463993966579437, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4a888ce2eb604eb7e53e68a2be530b0b6263f2efe34e7d87bc59f4199734d68f.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "4a8965d8b3979aa0da210f2f3cf83071a529509e53d4409842773e1221895c82", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "27f935757fe69f66b4587fd8142f86f3a7630db2628e169073df40f4ff883b41", "generation_seconds_batch": 17.961147152935155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.598835825920105, "target_z": -1.249999948525379, "ce": 6.300607204437256, "genuineness": 4.469690799713135, "identity": 0.37983667850494385, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4a8965d8b3979aa0da210f2f3cf83071a529509e53d4409842773e1221895c82.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": "4c89fdc16cfdcbd9c86a47c94d69e03c60c5fa0dfc71d88aa90bd7cb98bc90d4", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "316852eacea5edffa4ad9ceb86dc3905f21b26e3010b7b467e03a32335b579e1", "generation_seconds_batch": 13.699734495952725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4079253673553467, "target_z": -0.3183594118633353, "ce": 6.141753673553467, "genuineness": 4.18099308013916, "identity": 0.6293588876724243, "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": 0.120000000000001, "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/vn_VOLT_reg_high/4c89fdc16cfdcbd9c86a47c94d69e03c60c5fa0dfc71d88aa90bd7cb98bc90d4.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "4cb5497160b647ff565f0931e8f3b8ff319f7b036041c2b454721ca6041a798a", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "49fdd4816dea5f74206750bc567d2fdc7cb0c3341ef165d0b0f387be4752b418", "generation_seconds_batch": 14.634186455979943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6531143188476562, "target_z": -1.1875000128686553, "ce": 6.340320587158203, "genuineness": 4.457139015197754, "identity": 0.5360189080238342, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4cb5497160b647ff565f0931e8f3b8ff319f7b036041c2b454721ca6041a798a.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "4d065307a64ae1fdd130be68f37cd720ce25d9d73b73c6ee5d6c546fadb02f0c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "23a9603189e42ef7ef1893310e228c08f314a89ac6852cc4ac0c53b969d89bf6", "generation_seconds_batch": 21.166453338926658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8828628063201904, "target_z": 0.22851574577769126, "ce": 5.696964263916016, "genuineness": 3.9048471450805664, "identity": 0.4261634945869446, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4d065307a64ae1fdd130be68f37cd720ce25d9d73b73c6ee5d6c546fadb02f0c.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "4d1c5931c5e41e5ee7609cf9562efb8502a35f1a8c1a37ffe1b8fe56acccc56b", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bb7bc8be7002a83da5ca3a4fd9c53fdee5c6178c3af2b5deb022311b597f9dd7", "generation_seconds_batch": 15.980390753014944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.374936819076538, "target_z": -1.5078124404824695, "ce": 6.213237762451172, "genuineness": 4.369274139404297, "identity": 0.6982329487800598, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4d1c5931c5e41e5ee7609cf9562efb8502a35f1a8c1a37ffe1b8fe56acccc56b.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "4d28ef9932fbb83a4f824f7c99716ed52e72f4aaf583519d69dcfb2433659880", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f9610873b5fdc63ff541677a1756e93e4427de06d34caeedeb29e814f7779997", "generation_seconds_batch": 21.504841862013564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.089799642562866, "target_z": 0.4667968448390893, "ce": 5.720792293548584, "genuineness": 3.9173994064331055, "identity": 0.4929869472980499, "hypothesis": "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/vn_VOLT_reg_high/4d28ef9932fbb83a4f824f7c99716ed52e72f4aaf583519d69dcfb2433659880.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "4d2b7a4f9074c646f0f7693543e28f56a175b51036cf1b122ba00e87ce380736", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0320c03da53042bf22eebf73f5c0f39431cf413a9674ffa48d08c2ede74677e2", "generation_seconds_batch": 20.898361123050563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7277473211288452, "target_z": -1.1015625155496251, "ce": 6.117925643920898, "genuineness": 4.419482707977295, "identity": 0.7343399524688721, "hypothesis": "La porte 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/vn_VOLT_reg_high/4d2b7a4f9074c646f0f7693543e28f56a175b51036cf1b122ba00e87ce380736.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "4d9a9af12fe36b017611ac052987d7d41d729ff730b5a53b0e91537419f2248d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "203df6737e1b9e565b52f7cd814ac8018519b08eaf4a054c6f7988697f0923fd", "generation_seconds_batch": 19.82143739599269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7955955266952515, "target_z": -1.0234374930294785, "ce": 6.046441555023193, "genuineness": 3.886019229888916, "identity": 0.5166959166526794, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4d9a9af12fe36b017611ac052987d7d41d729ff730b5a53b0e91537419f2248d.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "4de019bc48c2c94e2fd36824141bede476886a309071a6ef734349511a517801", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "aedcd4df9239d3b1869bc2d1a978d9fb7cf83aef9a081e9256393584ed4d1618", "generation_seconds_batch": 20.018656234024093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7616714239120483, "target_z": -1.0625000042895518, "ce": 6.054384231567383, "genuineness": 4.381826400756836, "identity": 0.49738091230392456, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4de019bc48c2c94e2fd36824141bede476886a309071a6ef734349511a517801.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "4de32ce771a902abcaf977318270968da178102eea5f85de7d74c24f0732a926", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2d4615ce742e548f6c410bd526873e5c7b8e8398c8c42241d75790bb8a3a547a", "generation_seconds_batch": 21.125218773959205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9015209674835205, "target_z": 0.25000001715820697, "ce": 5.80021858215332, "genuineness": 3.886019229888916, "identity": 0.6304013729095459, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre ! Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4de32ce771a902abcaf977318270968da178102eea5f85de7d74c24f0732a926.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "4de4aad6a943b9134e951d3a08ae261c794d65dcb119e69f6ccfd01208f2ce3c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ec39c9f1e2854428b55738315fa6db85f9371f5e0bd7f83eb2d8bc26d9fd0d9d", "generation_seconds_batch": 22.10424585500732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.768456220626831, "target_z": -1.0546875294906681, "ce": 5.935244083404541, "genuineness": 4.162164688110352, "identity": 0.6573667526245117, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4de4aad6a943b9134e951d3a08ae261c794d65dcb119e69f6ccfd01208f2ce3c.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "4e0af340deb69b32eefd8bf9ae81e293e9c720f5e37f586fddfe402a921a8a49", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2ed1c40429b98b59e65f8d586c89f962b85ce44d4a9e9695aeed8777b1c3a54d", "generation_seconds_batch": 15.583915262017399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3885064125061035, "target_z": -1.4921874908847026, "ce": 6.125868320465088, "genuineness": 4.256305694580078, "identity": 0.5698217153549194, "hypothesis": "La porte 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/vn_VOLT_reg_high/4e0af340deb69b32eefd8bf9ae81e293e9c720f5e37f586fddfe402a921a8a49.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "4e1f2912ecbaf2a7fff6c885a9e176c50a2254647a4e484dcb2dc1321ba84198", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "52b7632a30f84ebb6e2862f480faf677ff3420b6de731a045a45c7ea854332ac", "generation_seconds_batch": 16.300116671947762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6395447254180908, "target_z": -1.2031249624664222, "ce": 6.205295085906982, "genuineness": 4.256305694580078, "identity": 0.47490406036376953, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4e1f2912ecbaf2a7fff6c885a9e176c50a2254647a4e484dcb2dc1321ba84198.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "4e22299a0e45b877542976f376b5603799b11cf73f936220609018a2ff109190", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "764d60504168ef5d6994917c03bde0642d828bde6a9c7689b808170dfbc97d2d", "generation_seconds_batch": 14.652993898023851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2324556112289429, "target_z": -1.6718749603216463, "ce": 6.038498878479004, "genuineness": 4.080576419830322, "identity": 0.6837397813796997, "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/vn_VOLT_reg_high/4e22299a0e45b877542976f376b5603799b11cf73f936220609018a2ff109190.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "4e7f4bd7c2f71e4d220b6fa4fa697118f48e4220e3fb46ed21a99f52fb5e428e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "fbc02ff4bc42cf53a6f069a68879a6d80a9c27eedab51ba2670e15cc79d0b876", "generation_seconds_batch": 16.621975144022144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9889628887176514, "target_z": -0.8007812063001916, "ce": 6.260893821716309, "genuineness": 3.9048471450805664, "identity": 0.36351653933525085, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4e7f4bd7c2f71e4d220b6fa4fa697118f48e4220e3fb46ed21a99f52fb5e428e.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "4f6afd6d0b3189741fd0069b4b18fe1dbf9954fae8659285db84681fbb694b65", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d4c41546e4eed7f9c0ccc8ac457253669a87aa66a197b6f71117c08a5756bee", "generation_seconds_batch": 15.51970797299873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.073773145675659, "target_z": -0.7031249281500083, "ce": 6.062326908111572, "genuineness": 4.306513786315918, "identity": 0.4145752787590027, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4f6afd6d0b3189741fd0069b4b18fe1dbf9954fae8659285db84681fbb694b65.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "4faf9c90f8e1e105e43322cbfbdb4d409205830e784d5b4e851f5cb805f37940", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18998619255f7d938eb577514ed8f795cc55b257e63f1754763c5e74d4325135", "generation_seconds_batch": 15.290704340091906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.619951009750366, "target_z": -0.074218716487877, "ce": 5.752562999725342, "genuineness": 4.111956596374512, "identity": 0.3707851767539978, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4faf9c90f8e1e105e43322cbfbdb4d409205830e784d5b4e851f5cb805f37940.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "4fcaefb305bad34707094e5e2044eed92f23fcee365f2d4bb05c08bf61e5b792", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3f53f157405f5c38ac8ec05fa5d03fc67533f2efb908273a416c19502059cbfe", "generation_seconds_batch": 15.908425524947233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4631394147872925, "target_z": -1.4062499935656725, "ce": 6.395919322967529, "genuineness": 4.331617832183838, "identity": 0.37149596214294434, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/4fcaefb305bad34707094e5e2044eed92f23fcee365f2d4bb05c08bf61e5b792.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "507d4bf24751d45114efe084840fbf1aa87478b078a595e4c8889a3e6e5aa937", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "59d53fb507a0304edcf304e2d9deac9e7391875c2476ec1d1f860a2078c1a295", "generation_seconds_batch": 22.39383153000381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.475773572921753, "target_z": -0.24023438934318864, "ce": 6.062326908111572, "genuineness": 3.6412534713745117, "identity": 0.6531452536582947, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/507d4bf24751d45114efe084840fbf1aa87478b078a595e4c8889a3e6e5aa937.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "50d3cb054f44d5aaf68f0345dd89f6a30533f1e59f6aa8eb66e43ca731a299d0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b62ecc9ea291362f8764433510985bc1184abacfaaa22b281e21fc1b5eb572e7", "generation_seconds_batch": 20.582374951103702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3926596641540527, "target_z": -0.33593737721158135, "ce": 6.213237762451172, "genuineness": 4.049196243286133, "identity": 0.7831273078918457, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/50d3cb054f44d5aaf68f0345dd89f6a30533f1e59f6aa8eb66e43ca731a299d0.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "50f587ee060f69b13a0dcfaeb39c78ac40fbe7684367d7bdce158d1fb6559812", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d8d44c70ddb695c55d77dddd0649bf201192433a6f59b9d481ad011d876b2e8f", "generation_seconds_batch": 20.796252400963567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4706850051879883, "target_z": -0.24609371112593734, "ce": 5.9431867599487305, "genuineness": 3.8169827461242676, "identity": 0.6055879592895508, "hypothesis": "I found the little box. It was beside the old window. We can look inside together!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/50f587ee060f69b13a0dcfaeb39c78ac40fbe7684367d7bdce158d1fb6559812.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "5114f3e7916a2fc95ccc8e419b5fc177bc3b710192425eccd9ee1c4165f5ec3c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fb62a90da74b938be97bac65a545e29b1269fe40d8ad58cf386cb4f364ec819d", "generation_seconds_batch": 16.230296044959687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6793181896209717, "target_z": -0.005859321782748686, "ce": 6.054384231567383, "genuineness": 3.9425034523010254, "identity": 0.4583888351917267, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5114f3e7916a2fc95ccc8e419b5fc177bc3b710192425eccd9ee1c4165f5ec3c.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "5119a84d854086f1842e1772a63ec582cc4bdde0e822e4a1691b7d0f64f438fb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "97f76de9d1b093415446feec202ba5baf9805ebfe82453b61842a9958715dad3", "generation_seconds_batch": 20.91957434802316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7888107299804688, "target_z": -1.031249967828362, "ce": 6.0146708488464355, "genuineness": 3.7040140628814697, "identity": 0.33861494064331055, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5119a84d854086f1842e1772a63ec582cc4bdde0e822e4a1691b7d0f64f438fb.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "514a3c010d252ccef5fb1bc2554f593aed92f2fbcf92fe4a62eb917c377c1572", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "01086c29d93febe943c8eb568cbabf0deb0c7ff6888a32a934dd8462a0fb8c47", "generation_seconds_batch": 20.90958300291095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0847110748291016, "target_z": 0.4609375230563406, "ce": 5.760505676269531, "genuineness": 3.8922953605651855, "identity": 0.6214707493782043, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/514a3c010d252ccef5fb1bc2554f593aed92f2fbcf92fe4a62eb917c377c1572.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "51c7a453ee59f6116e691ddca6663caffd4864df08f8e88db7145eef6fea5eda", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "be26ff824a6fd1500247c67d85235a78f32b373c1088cede00653ee8e54f296d", "generation_seconds_batch": 21.289261717931367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5198748111724854, "target_z": -0.18945323451761795, "ce": 5.808161735534668, "genuineness": 4.243753433227539, "identity": 0.22498247027397156, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/51c7a453ee59f6116e691ddca6663caffd4864df08f8e88db7145eef6fea5eda.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "523f027bc01c1c1cc91ae65b891fdf5341b7b04a3f9dbb05d96b168ec0d28c39", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "19d3ed48bcd032a7aad36c5f1336262a9fcbf0e8eb2c0f274976bcd49833c4cd", "generation_seconds_batch": 21.88644194090739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.701368808746338, "target_z": 0.019531255630036663, "ce": 5.974957466125488, "genuineness": 4.068024158477783, "identity": 0.48189449310302734, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/523f027bc01c1c1cc91ae65b891fdf5341b7b04a3f9dbb05d96b168ec0d28c39.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "526d80c3cfa4d50f0320c0a66540838b076a111fb34854c48835a9afeae49a32", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ba3f5315be0ed9d7b11e69f719adb159596a3c34d761672d7609c9fcdb093a6d", "generation_seconds_batch": 15.407074267044663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5649117231369019, "target_z": -1.2890624597854523, "ce": 6.316492557525635, "genuineness": 4.093128204345703, "identity": 0.3261656165122986, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/526d80c3cfa4d50f0320c0a66540838b076a111fb34854c48835a9afeae49a32.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "52f2d4a2e6d58b0adf2e09473f0683a410d80fb80ce47fd5dd059df966be4091", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d1b75b81e70f3ab714be65781f833a29a51e81fde5ec5e48fab19b41dd8e0650", "generation_seconds_batch": 19.728764593950473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6056206226348877, "target_z": -1.2421874737264955, "ce": 6.356205940246582, "genuineness": 4.68307638168335, "identity": 0.5362817645072937, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/52f2d4a2e6d58b0adf2e09473f0683a410d80fb80ce47fd5dd059df966be4091.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "54069bbfafa48e0cc6ed4fbdbf53553ca3558d0bb30fc2a0b77a982f4f2ad4d2", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "43f88494143392d8a4d924885a94ae994ba831aa28ecf0da357cd15a736d6894", "generation_seconds_batch": 20.212666030973196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.402076005935669, "target_z": -1.4765625412869354, "ce": 6.173524379730225, "genuineness": 4.268857479095459, "identity": 0.6071500182151794, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/54069bbfafa48e0cc6ed4fbdbf53553ca3558d0bb30fc2a0b77a982f4f2ad4d2.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "541bb868e605d957488f520e0a5b7110e9746b18914cc04a5aaef10b6407e2c1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b0ac6c138417107daa43052e340305399f130737306ef01b6f3934ff5911b9b7", "generation_seconds_batch": 20.481646318919957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5359015464782715, "target_z": 0.9804688130027912, "ce": 5.669164657592773, "genuineness": 3.9299514293670654, "identity": 0.5064336657524109, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "wer": 0.058823529411764705, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/541bb868e605d957488f520e0a5b7110e9746b18914cc04a5aaef10b6407e2c1.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "5421dbf067a11264316240be27ebbaf244fed6f894e7eb3dc1326e4572ca0bfa", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cb7412ee37a6701b7a1837cf84fe4b745923b42a4828a030e8501269c21f7b80", "generation_seconds_batch": 22.036047897068784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9931159019470215, "target_z": 0.355468632841618, "ce": 6.078212261199951, "genuineness": 4.030367851257324, "identity": 0.5468708276748657, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5421dbf067a11264316240be27ebbaf244fed6f894e7eb3dc1326e4572ca0bfa.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "e1f13da9dcdd57281554bd7ad1e5cc5ca4d9c524ecc229d595bb5a0e56718ba6", "generation_seconds_batch": 15.321507205022499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2867341041564941, "target_z": -1.6093750246649225, "ce": 6.372091293334961, "genuineness": 4.20609712600708, "identity": 0.5913146734237671, "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/vn_VOLT_reg_high/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "54705b0722e777d28d64920d0c1269c8ec98f7d180bb8075222bd885a4229c85", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "540e2783e0db64064974fef1cec6d23c6df9ae8acb7b8b28ace01887cd3944b6", "generation_seconds_batch": 15.249164565000683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3477975130081177, "target_z": -1.5390624769436594, "ce": 6.0305562019348145, "genuineness": 4.1998209953308105, "identity": 0.40572649240493774, "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/vn_VOLT_reg_high/54705b0722e777d28d64920d0c1269c8ec98f7d180bb8075222bd885a4229c85.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "54af167f14e8f0480740563d69dc6f0253f9e38e9d044c367c41d425dadb1ce2", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2bba9897daf72be3da51db454ce70c5b7394fc8668ab33572c001467decf0165", "generation_seconds_batch": 16.28369496704545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8939753770828247, "target_z": -0.910156265281528, "ce": 6.24500846862793, "genuineness": 4.262581825256348, "identity": 0.7497099041938782, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/54af167f14e8f0480740563d69dc6f0253f9e38e9d044c367c41d425dadb1ce2.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "55dcd4cd5cd5910dec8ce5ef63e0b8de1fbe19c6c120a24eda2e57cd7c3b7ded", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e227854c2705fe7bac4c781e05b6233dad74d97de6a628aebe652d7fef136afb", "generation_seconds_batch": 20.397494712960906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.223039150238037, "target_z": -0.5312499335119479, "ce": 6.1894097328186035, "genuineness": 4.281409740447998, "identity": 0.6877654790878296, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/55dcd4cd5cd5910dec8ce5ef63e0b8de1fbe19c6c120a24eda2e57cd7c3b7ded.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "570f848d29da25d885c0bd63577981e920a8a14b4623d6f596bdd8dcc750d560", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2455c26990b8d61a5ff99fff4b0605b02eb6bf8dec99f123113011a82ef760bb", "generation_seconds_batch": 21.12516679696273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.708914279937744, "target_z": 1.179687400804116, "ce": 6.1020402908325195, "genuineness": 3.5973212718963623, "identity": 0.24738523364067078, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/570f848d29da25d885c0bd63577981e920a8a14b4623d6f596bdd8dcc750d560.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "571f8fec2199ba6aa16db20ff5cee20a0c1c8e60a4053cc9cb3ed11e41026055", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fb9c5589e13c9aa9168e41578e977a8793a2b994ef466723ffc525ed45148baf", "generation_seconds_batch": 21.294805258046836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9965083599090576, "target_z": 0.35937493887388766, "ce": 5.418970584869385, "genuineness": 3.9676074981689453, "identity": 0.7048832774162292, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay de.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/571f8fec2199ba6aa16db20ff5cee20a0c1c8e60a4053cc9cb3ed11e41026055.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "573513dca65c424e11a882d9434a8f131e9cba73ff0c889f713d71c75d2f994f", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e5bda4ad26189cc600703c405bca42353d7088d083bca5a1acdfc0e140a6852e", "generation_seconds_batch": 15.547946182079613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3003038167953491, "target_z": -1.5937499378014996, "ce": 5.998785495758057, "genuineness": 4.143336772918701, "identity": 0.588567852973938, "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/vn_VOLT_reg_high/573513dca65c424e11a882d9434a8f131e9cba73ff0c889f713d71c75d2f994f.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": "57924497e4b5d7f64793fa0e337baaab73e2140f56ea1d501ee632582ed6db58", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The road turns left behind the bridge.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f97218ca1b0f14acbceab08011c85102140e875aedddaf0a5fd2ab8b5ff6a4cd", "generation_seconds_batch": 14.553001404041424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2060770988464355, "target_z": -0.5507811891419846, "ce": 6.229123115539551, "genuineness": 3.7918784618377686, "identity": 0.4127296209335327, "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/vn_VOLT_reg_high/57924497e4b5d7f64793fa0e337baaab73e2140f56ea1d501ee632582ed6db58.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "579b7cbb24400036030f2b549d5d6dc005552349d0497bf7cd32fc5628cdd083", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4bfe1e8e20dbb5f2058f8933581c571081eee1e58565fd981fb35a2c3b32ad1e", "generation_seconds_batch": 21.870387542061508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9889628887176514, "target_z": -0.8007812063001916, "ce": 6.24500846862793, "genuineness": 4.319066047668457, "identity": 0.6464706659317017, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/579b7cbb24400036030f2b549d5d6dc005552349d0497bf7cd32fc5628cdd083.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "57c5be0a30c990f30e9c74ea0a387559c15b19451339737eb28aef30226dcff1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4f70f48b01c42d447921f5e3b147cc64d207a22811cbe5a4d2db30e862bc7eee", "generation_seconds_batch": 21.341941136983223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9584312438964844, "target_z": -0.8359374115279953, "ce": 6.213237762451172, "genuineness": 4.545003414154053, "identity": 0.7359551191329956, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/57c5be0a30c990f30e9c74ea0a387559c15b19451339737eb28aef30226dcff1.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "57c97ac36b083fe932343fe1c21c1c3839538c33b45d81beb18cc92938a68f20", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6c9031af6055d9ddce593ea1fce6981b25253a335538aeb4ab4bf17ce709cec6", "generation_seconds_batch": 15.780281141051091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4631394147872925, "target_z": -1.4062499935656725, "ce": 6.23706579208374, "genuineness": 4.369274139404297, "identity": 0.6225082874298096, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/57c97ac36b083fe932343fe1c21c1c3839538c33b45d81beb18cc92938a68f20.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "57e8cd7d8b5461b5dfe5e473af725ab9c35332206e532d83ad22375543ebb0ac", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4a8d144916f73f9adecc549dd5df5d33b06b2a6b6d132b62a27b5e481b2a2c80", "generation_seconds_batch": 15.907162116025575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2867341041564941, "target_z": -1.6093750246649225, "ce": 6.403861999511719, "genuineness": 4.20609712600708, "identity": 0.5506907105445862, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/57e8cd7d8b5461b5dfe5e473af725ab9c35332206e532d83ad22375543ebb0ac.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "57eb8349124c28879cbc31d6ae923cb1cbbddfe367c057e94d7642ab6073d14c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "58f270aaab258879eb57df40bc0b153aa49926bebe3538c9d3bde1fbd827e04f", "generation_seconds_batch": 20.94663986598607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.792963743209839, "target_z": 0.1249998713134477, "ce": 5.764476776123047, "genuineness": 4.281409740447998, "identity": 0.5737490653991699, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/57eb8349124c28879cbc31d6ae923cb1cbbddfe367c057e94d7642ab6073d14c.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "5822bf2a028a2f59d6ef61a6b8c6141148cc48fd629a0e6ae9f168685fb6429c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "48b5c8d2b7e9ecd654c781fcdac1443f424b0f5ea52514f1d0a2a6e152d8b508", "generation_seconds_batch": 21.768480589031242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8329119682312012, "target_z": -0.9804688130027912, "ce": 6.213237762451172, "genuineness": 4.381826400756836, "identity": 0.3014567196369171, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5822bf2a028a2f59d6ef61a6b8c6141148cc48fd629a0e6ae9f168685fb6429c.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "584dfcfed6a8bc0dd420744f060945a9751bf03b184ab5c990966a74153b2f94", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "aa61a118e5a2cf98d5d8165b664db4708afa5604d8a5aa59dc043526106af670", "generation_seconds_batch": 15.249164565000683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6191902160644531, "target_z": -1.2265625241287286, "ce": 6.141753673553467, "genuineness": 4.287685871124268, "identity": 0.6876714825630188, "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/vn_VOLT_reg_high/584dfcfed6a8bc0dd420744f060945a9751bf03b184ab5c990966a74153b2f94.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": "5887e67d435319c5a628e8bfa6457afeaa4a605e03d2252b4d36c8ae1a3467c4", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab3132c0024d9ba0586f41b9157a4bf5a8d701164ac858f77ebd4cacd5963e20", "generation_seconds_batch": 21.01419704791624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.390963315963745, "target_z": -0.33789066749337193, "ce": 6.125868320465088, "genuineness": 3.8420867919921875, "identity": 0.5158798694610596, "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/vn_VOLT_reg_high/5887e67d435319c5a628e8bfa6457afeaa4a605e03d2252b4d36c8ae1a3467c4.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "589abb5fe5bddde7db0ec82e0d2e99218a39ccf00137211ae339b9e68dadaa1a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e664992c0a2f13d37ce1c6740aa3ec70de63923a5d33d5aff4d346d22ef432c2", "generation_seconds_batch": 19.829309803899378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.342534065246582, "target_z": 0.7578123890078486, "ce": 5.585766792297363, "genuineness": 3.553389072418213, "identity": 0.26028597354888916, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/589abb5fe5bddde7db0ec82e0d2e99218a39ccf00137211ae339b9e68dadaa1a.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "595d26a26a2f17741d34b8b13f1f05151a065a1f38f63c42a0b12d30f8041acb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b461b6702310cff05af56fd5507bc1eb084654e360e324f39dab3afd234fd09a", "generation_seconds_batch": 20.143000334966928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6463295221328735, "target_z": -1.1953124876675387, "ce": 5.95112943649292, "genuineness": 4.331617832183838, "identity": 0.5846918225288391, "hypothesis": "La porte 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/vn_VOLT_reg_high/595d26a26a2f17741d34b8b13f1f05151a065a1f38f63c42a0b12d30f8041acb.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "5acfc24c854157d299e4da211632cfb443f0bdb9f8c9f4c2a72e014da73a1910", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "96922cd05360dc548bb7985cf6c1ae5c4675b72c125cb2cf8b7622433d6aa3e8", "generation_seconds_batch": 20.80539725208655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8329119682312012, "target_z": -0.9804688130027912, "ce": 5.927301406860352, "genuineness": 3.886019229888916, "identity": 0.7272714376449585, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen het er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5acfc24c854157d299e4da211632cfb443f0bdb9f8c9f4c2a72e014da73a1910.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "5b3060b1c8b14a5bb01509c25cb3dfb796d3627e69cc5b47d2c40cf26237bc37", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6adf4f38f4bb025cb67918893d7016611de698295d4d46b56538285687e3da80", "generation_seconds_batch": 20.988095427979715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6531143188476562, "target_z": -1.1875000128686553, "ce": 5.974957466125488, "genuineness": 4.20609712600708, "identity": 0.5827239751815796, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5b3060b1c8b14a5bb01509c25cb3dfb796d3627e69cc5b47d2c40cf26237bc37.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": "5b73382d08b0859a0bce1c1aad78f0951cc2628b9708f5eeb46b1b957bae3915", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "c2fffd7106333e11c94aa0a71bd311b62532c0224a1d21b5b9238b067bf2a918", "generation_seconds_batch": 15.047432180959731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.009317398071289, "target_z": -0.7773436446378853, "ce": 5.879645347595215, "genuineness": 4.20609712600708, "identity": 0.5434131622314453, "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/vn_VOLT_reg_high/5b73382d08b0859a0bce1c1aad78f0951cc2628b9708f5eeb46b1b957bae3915.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "5c75aa4b70375edc05136edada271ccac32333f9aa6518024c170f0f1603ce11", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c7a206013e6aa925297f8def4e1610c2ac461dcc933740f73f3bea80bd5bf49f", "generation_seconds_batch": 22.70179081801325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3003038167953491, "target_z": -1.5937499378014996, "ce": 6.23706579208374, "genuineness": 4.080576419830322, "identity": 0.33605557680130005, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5c75aa4b70375edc05136edada271ccac32333f9aa6518024c170f0f1603ce11.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "5c99b321d20cb11421a0cd790189bf9611e70d35ad288996aaabe244b889dd69", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "47d7f9bde9f985096d536bcfd4f22e64ece997314962a8e289eaf9b38fbb1e6e", "generation_seconds_batch": 19.141490117996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6191902160644531, "target_z": -1.2265625241287286, "ce": 6.268836498260498, "genuineness": 4.770940780639648, "identity": 0.5654680728912354, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5c99b321d20cb11421a0cd790189bf9611e70d35ad288996aaabe244b889dd69.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": "5cca81085955712651d362497d32e03a18fa209a07c2a17123cb10af383ea279", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "66ff0eccb01bca0c0ab85956e71d3aad2f8ca1b9e9558a036b3546875b7a29bc", "generation_seconds_batch": 14.231758348061703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3587355613708496, "target_z": -0.37499988847165466, "ce": 6.109982967376709, "genuineness": 4.093128204345703, "identity": 0.5497192144393921, "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/vn_VOLT_reg_high/5cca81085955712651d362497d32e03a18fa209a07c2a17123cb10af383ea279.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "5ce5c44d36fbbf9245b3df43f54990f333d7f3d5afb3c7a6f683d172254db7de", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "7a62a8f5b8a52cc975abebd302462e66e9c175567d5196e5342384b3cfb3fb1c", "generation_seconds_batch": 21.992718623019755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.002532482147217, "target_z": -0.7851562567024246, "ce": 6.221180438995361, "genuineness": 3.9425034523010254, "identity": 0.4228774905204773, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5ce5c44d36fbbf9245b3df43f54990f333d7f3d5afb3c7a6f683d172254db7de.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "5d430ddb662beba5690c9b2a6e53f1cc58708d7a4775ab6e3ce2e39b499fb86d", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f0cb22eb947e0b7a7a293be90af0b99e0f8ec58df5f5088b342a8855be6b2fe", "generation_seconds_batch": 16.19314716104418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.58526611328125, "target_z": -1.2656250353888019, "ce": 6.149696350097656, "genuineness": 4.545003414154053, "identity": 0.7565875053405762, "hypothesis": "La porte 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/vn_VOLT_reg_high/5d430ddb662beba5690c9b2a6e53f1cc58708d7a4775ab6e3ce2e39b499fb86d.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "5d5265365baf070679b09b52066aa2450aef78e838ef6d77b827423c515d0423", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "93402d2563c806a2ee00383e4e83eaa915e63b7ee2fd4dbc72101fe2c125f729", "generation_seconds_batch": 15.803797219065018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.390963315963745, "target_z": -0.33789066749337193, "ce": 6.23706579208374, "genuineness": 3.9299514293670654, "identity": 0.4064861536026001, "hypothesis": "Ik 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/vn_VOLT_reg_high/5d5265365baf070679b09b52066aa2450aef78e838ef6d77b827423c515d0423.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "5d70e3b454990645e1e2394cb7d847c0591d777e24783b47a35833253d1e3d7e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1223e66bf48508b66cff6d16ab8a226810dc0251cd25c55ee8b17bb8accbbe42", "generation_seconds_batch": 20.524754739017226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7802422046661377, "target_z": 0.1103514295909202, "ce": 5.80021858215332, "genuineness": 3.6412534713745117, "identity": 0.4807922840118408, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5d70e3b454990645e1e2394cb7d847c0591d777e24783b47a35833253d1e3d7e.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "5d7a07d19765648b1d62295bc784296c861be83010974be74be7a293293137c3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a9b6c49568048faf3e13ece3ccca8072cec0391ff9920df6119ea91cfc0d4a4b", "generation_seconds_batch": 19.918218408012763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6055331230163574, "target_z": -0.09082044849219512, "ce": 6.109982967376709, "genuineness": 3.848362922668457, "identity": 0.635287344455719, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5d7a07d19765648b1d62295bc784296c861be83010974be74be7a293293137c3.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "92a9abca8913b10d7cb2c9f8a95d3f08b5ea945897809183e9ba4306beb9c9f6", "generation_seconds_batch": 16.634022359969094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5309876203536987, "target_z": -1.3281249710455256, "ce": 6.070269584655762, "genuineness": 4.394378662109375, "identity": 0.6174725294113159, "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/vn_VOLT_reg_high/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "5e141463c338bcd5c68ce7a0ce8fad8b063491c344902dc35cab25f8be5278ca", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cd6b001d333ce343567ada9291ce471d0197f8013d9bf4402915c45e8186be22", "generation_seconds_batch": 21.23021723004058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5445572137832642, "target_z": -1.3125000214477587, "ce": 6.09409761428833, "genuineness": 4.394378662109375, "identity": 0.4099532961845398, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5e141463c338bcd5c68ce7a0ce8fad8b063491c344902dc35cab25f8be5278ca.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": "5e66435ed338657de4efdf0138478d100855d8f378ca8fcf03a9b8e5fbbac44f", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I wrote the number on the envelope.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "28be15cdbd9abbb0f18746b46c18e6011a8eb3bbc28194f54dd2e2f4f5b40ed5", "generation_seconds_batch": 15.368403851985931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8634437322616577, "target_z": -0.9453124705093318, "ce": 6.181467056274414, "genuineness": 3.7040140628814697, "identity": 0.4767616093158722, "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": 0.120000000000001, "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/vn_VOLT_reg_high/5e66435ed338657de4efdf0138478d100855d8f378ca8fcf03a9b8e5fbbac44f.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": "5e7470f711e2039d88aef23eb92bfa8bcc1a74fd4df63fd619d79504696b634f", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "b22bb0cb9a20d38373062ae7d5f78f7bd7323e017393e68893d972156de906cf", "generation_seconds_batch": 15.854356413008645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.134836435317993, "target_z": -0.6328125176944009, "ce": 6.09409761428833, "genuineness": 4.268857479095459, "identity": 0.581441342830658, "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/vn_VOLT_reg_high/5e7470f711e2039d88aef23eb92bfa8bcc1a74fd4df63fd619d79504696b634f.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": "5e75033c525ef84c834e2f2b1789564b0a48cdb60757ca2306be9b1219118d82", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "15647a70bda4186ad8805f468153181c92498c2021a31ee90d8c9c68fe48fcd5", "generation_seconds_batch": 13.83209074207116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.961823582649231, "target_z": -0.8320312427613814, "ce": 5.990842819213867, "genuineness": 4.362998008728027, "identity": 0.541621208190918, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis le bien and verify the two dernier chiffres. Appelle moi quand tu aurais un moment.", "wer": 0.2727272727272727, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5e75033c525ef84c834e2f2b1789564b0a48cdb60757ca2306be9b1219118d82.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "5e8fa45daf020f6f10c3d7eb8e51ce638114e67517cedabd66e8cfaa83f88db8", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "39dbb2d1186b2aa7ccb49eda0576cf1bc721040a9ec4d5b61ff67635be2554fe", "generation_seconds_batch": 21.205840138019994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6394572257995605, "target_z": -0.051757937232121784, "ce": 6.165581703186035, "genuineness": 3.8295347690582275, "identity": 0.543338418006897, "hypothesis": "Ik 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/vn_VOLT_reg_high/5e8fa45daf020f6f10c3d7eb8e51ce638114e67517cedabd66e8cfaa83f88db8.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "5e9089b45a66aefedb99324814a85d32be2c89f41c1731b674ae97cf1da2ab3d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28ff9b3a009fd9a483ee2f8ba5ed4ec26e247c1521beca5640ddc92018b602fb", "generation_seconds_batch": 19.82850195397623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4427849054336548, "target_z": -1.4296875552279786, "ce": 6.181467056274414, "genuineness": 4.406930446624756, "identity": 0.6936392784118652, "hypothesis": "La porte 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/vn_VOLT_reg_high/5e9089b45a66aefedb99324814a85d32be2c89f41c1731b674ae97cf1da2ab3d.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": "5ed2ab7a39eab0c277f08758b2c392e49183d5bc1b1bf2d43d058783a0cd84e9", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f26f8b9065d51f90d959b2dc010a1c6b6b2ae50362b4d7925451910ceb635ad2", "generation_seconds_batch": 20.559555140091106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.045698404312134, "target_z": 0.4160156900135186, "ce": 6.022613525390625, "genuineness": 4.036643981933594, "identity": 0.6646182537078857, "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/vn_VOLT_reg_high/5ed2ab7a39eab0c277f08758b2c392e49183d5bc1b1bf2d43d058783a0cd84e9.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": "5f094d6e5bda03f94dcd173972c524f9cebbe29568c347e0b960eaea8991c9b8", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Someone moved the little blue chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd75fc70fa1da91faaa5c7fedbf79e5834ba221046aac239c7697f347f347875", "generation_seconds_batch": 22.350776192964986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2976720333099365, "target_z": -0.4453125734585736, "ce": 6.165581703186035, "genuineness": 3.773050308227539, "identity": 0.4030885100364685, "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/vn_VOLT_reg_high/5f094d6e5bda03f94dcd173972c524f9cebbe29568c347e0b960eaea8991c9b8.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "5f179a83c813148b2487339d8a23264450feaea12916cfb79e756f79ec2566c4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f35184c62f88c43c46f1b9af2daeeb723409961e82e94b00a918d7a0560b4b8", "generation_seconds_batch": 21.77492333203554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6259750127792358, "target_z": -1.218750049329845, "ce": 6.125868320465088, "genuineness": 4.143336772918701, "identity": 0.5643469095230103, "hypothesis": "La porte 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/vn_VOLT_reg_high/5f179a83c813148b2487339d8a23264450feaea12916cfb79e756f79ec2566c4.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "5f48a2550a1be3c43151a0723d50479fb344676c05979695263368289c5e5dbe", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5a02380485c6df256c5612fdeb69eea3e12ac4020a74f585a9dd0a3db1407902", "generation_seconds_batch": 19.728764593950473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6870384216308594, "target_z": -1.148437501608582, "ce": 6.23706579208374, "genuineness": 4.796044826507568, "identity": 0.7551426291465759, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/5f48a2550a1be3c43151a0723d50479fb344676c05979695263368289c5e5dbe.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "605e0694f8494814211971affbcee045940bc8b19212ac2a411a41933dcf91c1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3212cc11709b6b57ba5356b142bd1ef9144308abad2fbff596a63d85a661ba69", "generation_seconds_batch": 21.047867411980405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2935189008712769, "target_z": -1.601562549866039, "ce": 5.665193557739258, "genuineness": 3.9927117824554443, "identity": 0.5051693916320801, "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/vn_VOLT_reg_high/605e0694f8494814211971affbcee045940bc8b19212ac2a411a41933dcf91c1.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "60abfca703a79aa5b75b75ecd528579ba9562cff4c47515c0b5d8288c959551e", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "aa3c67e2f978b77f635ffd806ec21041ffeba4ff8bc620b0491f78eaacc44e00", "generation_seconds_batch": 14.855929463054053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.23706579208374, "genuineness": 4.375550270080566, "identity": 0.41141819953918457, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/60abfca703a79aa5b75b75ecd528579ba9562cff4c47515c0b5d8288c959551e.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "620441350ba974767e8349651598f1abe20030e1f01bae15ebd8814e06121777", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "efaa0dc4c1a917ec1bc36dfb3a4f72053471c837b83840934672c94b820968c5", "generation_seconds_batch": 19.29990041104611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2128617763519287, "target_z": -0.542968851608757, "ce": 6.09409761428833, "genuineness": 3.9173994064331055, "identity": 0.7847886085510254, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/620441350ba974767e8349651598f1abe20030e1f01bae15ebd8814e06121777.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "621327ddd96bd0c97750035e5f032ba3b36207c88664eb83785f9923ebf28133", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "05fadc4a64b910e35a5d634e002927d66575d46929778d70c9b728cea3160653", "generation_seconds_batch": 15.404041143017821, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9354450702667236, "target_z": 0.2890625284182803, "ce": 6.1020402908325195, "genuineness": 3.4623863697052, "identity": 0.32683348655700684, "hypothesis": "Ik 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/vn_VOLT_reg_high/621327ddd96bd0c97750035e5f032ba3b36207c88664eb83785f9923ebf28133.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "622efeb8a10f11a5adffbef4064003a673179a49a93d08ebb836ddbf733409c9", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d3489538f01ed46bd774583fc6ac653bd2fbd85c71bcffabf1dc06ec785f1c42", "generation_seconds_batch": 15.845627593924291, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5581269264221191, "target_z": -1.296874934584336, "ce": 6.141753673553467, "genuineness": 4.356721878051758, "identity": 0.7320849895477295, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/622efeb8a10f11a5adffbef4064003a673179a49a93d08ebb836ddbf733409c9.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": "626364be46fcf8a5b8f2fa6fe18fd186b71e799fdb70465de17c0cd053c24883", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f551212a0a461bc4a7a1c6d394930d8ca8dfe2b44b4e5572a315657638dc1d88", "generation_seconds_batch": 21.730097285937518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9414691925048828, "target_z": -0.8554686671580319, "ce": 6.133810997009277, "genuineness": 3.7542223930358887, "identity": 0.5304245948791504, "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/vn_VOLT_reg_high/626364be46fcf8a5b8f2fa6fe18fd186b71e799fdb70465de17c0cd053c24883.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "62ba214bbfb363a2c36ec24d0a9d62e75894f7ecb2805e8d1ab22f6b641386df", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6568d087cacdd2ccc9366fd4911442cd86d1b4f70b5e770485244e81924b3e9b", "generation_seconds_batch": 21.28922697994858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5920509099960327, "target_z": -1.2578125605899184, "ce": 6.141753673553467, "genuineness": 3.8922953605651855, "identity": 0.32810962200164795, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/62ba214bbfb363a2c36ec24d0a9d62e75894f7ecb2805e8d1ab22f6b641386df.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "634eae6204852e2f18a2072e8aae1a18b09440f8d5f9521912a10dd7cbc62973", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5944e184233378d4eb5e813034713bb19abf3d642406697c8a2d9a291a002adc", "generation_seconds_batch": 15.571971231023781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6259750127792358, "target_z": -1.218750049329845, "ce": 6.197352409362793, "genuineness": 4.344170093536377, "identity": 0.5684648752212524, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/634eae6204852e2f18a2072e8aae1a18b09440f8d5f9521912a10dd7cbc62973.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "635fa4df97f3152efacac6078a04c56bf0605dc6229619bddc2fd94bd47a8428", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "84533ddf120c2f82b1b25d8c09df2ed623916366edac0623f8a578dc021a8d58", "generation_seconds_batch": 19.902222548960708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.659899115562439, "target_z": -1.1796875380697718, "ce": 6.141753673553467, "genuineness": 4.65797233581543, "identity": 0.7291540503501892, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/635fa4df97f3152efacac6078a04c56bf0605dc6229619bddc2fd94bd47a8428.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "63d3fb1b929ae74633a1eb04bdb8dc1b9fbd521f4f90090ea4aa105a751ca64f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7e32faa32a40ad7926b9de55b0a94e0c2dbbe9c7a5a2cdb0e7da732d028af7a1", "generation_seconds_batch": 15.479837257997133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8329119682312012, "target_z": -0.9804688130027912, "ce": 6.1894097328186035, "genuineness": 4.607763767242432, "identity": 0.4835459589958191, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/63d3fb1b929ae74633a1eb04bdb8dc1b9fbd521f4f90090ea4aa105a751ca64f.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "649b5102e91b21c249f67069072123032ab82840102904dee5491f9e5315d598", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "138ef89d84bba1fec30d08b3b49b8c9b0234366a30fa1264dcf5fb1cc9a42e10", "generation_seconds_batch": 21.28678158496041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7454700469970703, "target_z": 0.07031241045560736, "ce": 6.292664527893066, "genuineness": 4.017816066741943, "identity": 0.646527886390686, "hypothesis": "Ik 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/vn_VOLT_reg_high/649b5102e91b21c249f67069072123032ab82840102904dee5491f9e5315d598.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "64b28b47117f87199b3cc4341ce39cd3c61e7086023e2d2f5b904f4bc1a3e79e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6ef7bd4aec664a2f0263763bfe6c016b9bca44fa2e297af8c594e43e97d87f52", "generation_seconds_batch": 22.055210676044226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9889628887176514, "target_z": -0.8007812063001916, "ce": 6.1894097328186035, "genuineness": 4.030367851257324, "identity": 0.505257248878479, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/64b28b47117f87199b3cc4341ce39cd3c61e7086023e2d2f5b904f4bc1a3e79e.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "656f3f9257a738047d686fe2d76822d0378968988f36d91b7c538a69bebd0a4e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "9bd34e08960f8c90ed37542abb498f179ab6bfec611ab2b02d1178a72c78f984", "generation_seconds_batch": 15.290704340091906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6521787643432617, "target_z": -0.03710949550959428, "ce": 5.9431867599487305, "genuineness": 3.998987913131714, "identity": 0.40907222032546997, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/656f3f9257a738047d686fe2d76822d0378968988f36d91b7c538a69bebd0a4e.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": "65f1e16d9bfbf67517492fc4b99f06f72028855ad39343b7cc56043d7017a720", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6cd51deaf5cd7cd9c8165fef023ae5ae164745bab47e84eb54d0422dfeb6c8ce", "generation_seconds_batch": 14.643346751923673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.436760902404785, "target_z": -0.2851562223860106, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.7299651503562927, "hypothesis": "Mon message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi, quand nous pourrons parler?", "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/vn_VOLT_reg_high/65f1e16d9bfbf67517492fc4b99f06f72028855ad39343b7cc56043d7017a720.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "660eafdeb1ebf913dcb5a3d2790d87dc621496511459b29a7ee9961a7382c4f4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "40e7898032e898212189b99a1960d0498a2b8b866f977b3e9d401a91ece8a1d3", "generation_seconds_batch": 15.498747089062817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3960518836975098, "target_z": -0.33203134571062326, "ce": 6.109982967376709, "genuineness": 4.086852550506592, "identity": 0.2306661456823349, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/660eafdeb1ebf913dcb5a3d2790d87dc621496511459b29a7ee9961a7382c4f4.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "6659f6ab71362159ba7195d3224ee5b8de20b9e6c87719e789c9f18b33744f30", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b64e7e5e1fd58a15355eecdcd91c95f321199121c80d6fc7fa9935c271f2cea0", "generation_seconds_batch": 15.413547935080715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.659899115562439, "target_z": -1.1796875380697718, "ce": 6.4515180587768555, "genuineness": 4.381826400756836, "identity": 0.3461151719093323, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6659f6ab71362159ba7195d3224ee5b8de20b9e6c87719e789c9f18b33744f30.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "666ff6e9c27ddede444b703d496b107240d3b2014e8089dc2676137af5149195", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "620b8f27295088549301f27cc8f166132587bcdcdae5d865b35e2fcdb8d446f9", "generation_seconds_batch": 18.57311585196294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.610621929168701, "target_z": -0.08496085217813486, "ce": 6.038498878479004, "genuineness": 3.7291181087493896, "identity": 0.6062324643135071, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/666ff6e9c27ddede444b703d496b107240d3b2014e8089dc2676137af5149195.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "66c23901165abb98203a2a6d72bfd6e34d1446c8410c8e5097b5e9add6f63d58", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1acd5b53c7df8033349a140dc17aa94fabb5dd85da55f333fd305eca40053f4d", "generation_seconds_batch": 20.212666030973196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9550387859344482, "target_z": -0.839843717560265, "ce": 6.078212261199951, "genuineness": 4.469690799713135, "identity": 0.6785333156585693, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/66c23901165abb98203a2a6d72bfd6e34d1446c8410c8e5097b5e9add6f63d58.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "66c8957c31814b145aa015fd01025a7d7f3c04e229e37cbd785180b7543d85ce", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d5d5f1cb21de428c0731b953002286cebb5e03a1355b3ae3402c94e957dd685f", "generation_seconds_batch": 15.269713629968464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5174179077148438, "target_z": -1.3437500579089485, "ce": 6.165581703186035, "genuineness": 4.507347106933594, "identity": 0.677479088306427, "hypothesis": "La porte 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/vn_VOLT_reg_high/66c8957c31814b145aa015fd01025a7d7f3c04e229e37cbd785180b7543d85ce.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "674e5c288da9ce3c6c8d31553d52051d7bb12eabcd91e0e3f57fb569d60287b3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0b77bd15483cc3590d12efa2a6ad8ae025417ac1b1fef8ea95956d36befdfbbf", "generation_seconds_batch": 20.207972623058595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.361367106437683, "target_z": -1.5234375273458924, "ce": 6.141753673553467, "genuineness": 4.042920112609863, "identity": 0.2099923938512802, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/674e5c288da9ce3c6c8d31553d52051d7bb12eabcd91e0e3f57fb569d60287b3.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "677b0cde07f51671c744387eab25e601ab11868fa7ca95fa989591b249810793", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9423a0c8dc68aedbd2f7a0aa87a5db85fa07b541eb5b87b42e7baadc2d8fe9ec", "generation_seconds_batch": 22.73613178404048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7006080150604248, "target_z": -1.132812552010815, "ce": 5.990842819213867, "genuineness": 4.20609712600708, "identity": 0.6714867353439331, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/677b0cde07f51671c744387eab25e601ab11868fa7ca95fa989591b249810793.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": "68565e34079ad6420a91820e13e50c84e799fd1e7e5bdcc2ae2aef2a4cb375fe", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "491a214760ef98eaa71fa652c026c3014a0bdc1dc6a2cfa5095e77e0b316bd31", "generation_seconds_batch": 15.899518066085875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7481017112731934, "target_z": -1.0781250911529745, "ce": 5.967014789581299, "genuineness": 3.9927117824554443, "identity": 0.42656609416007996, "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/vn_VOLT_reg_high/68565e34079ad6420a91820e13e50c84e799fd1e7e5bdcc2ae2aef2a4cb375fe.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "68fc9366c0b7824c65d29c1a88adb1c3197cd554cb42204f16bb47cf9a3b0576", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "85a24b04dcfdb0dc55fb5b9ac0fdf1b47d54ad3dab5007bd869a63795c0155a8", "generation_seconds_batch": 15.379773881984875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7209625244140625, "target_z": -1.1093749903485086, "ce": 6.125868320465088, "genuineness": 4.168440818786621, "identity": 0.7173540592193604, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/68fc9366c0b7824c65d29c1a88adb1c3197cd554cb42204f16bb47cf9a3b0576.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "6918054d19699294bf8b453451c0c8668a4445c949188e7883dad5dedb8d78f9", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cb298a08b7b39bec8f2478b7869891a31127a4711a25dfc0888dd1b4fc78b0de", "generation_seconds_batch": 15.924648014013655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6124054193496704, "target_z": -1.234374998927612, "ce": 6.205295085906982, "genuineness": 4.111956596374512, "identity": 0.42425960302352905, "hypothesis": "Ten que he encrotado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.17647058823529413, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6918054d19699294bf8b453451c0c8668a4445c949188e7883dad5dedb8d78f9.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "69261978f619c653c3b852c08939a5ec79fa8aca6f19255dfc758cf5f1c2ba0f", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c682dc6942d48532a586b6eda4e7926df8a62bf524241f63598cc260f58a1967", "generation_seconds_batch": 14.855929463054053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6259750127792358, "target_z": -1.218750049329845, "ce": 6.38003396987915, "genuineness": 4.7332844734191895, "identity": 0.7496691942214966, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/69261978f619c653c3b852c08939a5ec79fa8aca6f19255dfc758cf5f1c2ba0f.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "694caf274278edf071cdc24cfe846b0a6989c057317b53793cdd26f08cd0800b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7ba686d1ad90a2046476ba9c673705f78f0c5c47e9e90e51593f9cd7aa28bf9d", "generation_seconds_batch": 21.35887040407397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.66235613822937, "target_z": -0.02539057741278535, "ce": 5.879645347595215, "genuineness": 3.722842216491699, "identity": 0.6396519541740417, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/694caf274278edf071cdc24cfe846b0a6989c057317b53793cdd26f08cd0800b.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "69d1ad5622e6d06cf0e8d3caba0593b5fa94ec17ff08715a4cfa9c06a149cb73", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "31955de6cc5bf9562de27526d6f1c99be6fc24efc1ef373d36fd4bdb55c4e675", "generation_seconds_batch": 14.566136463079602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3003038167953491, "target_z": -1.5937499378014996, "ce": 6.125868320465088, "genuineness": 4.419482707977295, "identity": 0.6900721788406372, "hypothesis": "La porte 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/vn_VOLT_reg_high/69d1ad5622e6d06cf0e8d3caba0593b5fa94ec17ff08715a4cfa9c06a149cb73.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "6a1ea578dbc8959216ff2c9fc7023015da7d6f430ea4f7d4d980860f63652698", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b947da7bb45fe64a9768cf7bd2bcda14d904b90a5f88b830577bcd523eb799c1", "generation_seconds_batch": 20.408677516970783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9720008373260498, "target_z": -0.8203124619302283, "ce": 6.133810997009277, "genuineness": 4.231201171875, "identity": 0.6771409511566162, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6a1ea578dbc8959216ff2c9fc7023015da7d6f430ea4f7d4d980860f63652698.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "6a1f711372c73f37d917a47423645e251f4cbd9c392f857d4a52395504b40a37", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8ebc37b55da1ca77408045d4957110c8c1c9e10bf84481bb8c7defd2f19b5dbf", "generation_seconds_batch": 15.840456769918092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3885064125061035, "target_z": -1.4921874908847026, "ce": 6.213237762451172, "genuineness": 4.287685871124268, "identity": 0.6019154787063599, "hypothesis": "La porte 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/vn_VOLT_reg_high/6a1f711372c73f37d917a47423645e251f4cbd9c392f857d4a52395504b40a37.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2fa06787a9bb970faf66026c9457c53e4984b752f39ee7b83a17e06cbe061ddf", "generation_seconds_batch": 14.613188895047642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.476709008216858, "target_z": -1.3906250439679053, "ce": 6.308549880981445, "genuineness": 3.9299514293670654, "identity": 0.35048341751098633, "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/vn_VOLT_reg_high/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.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": "6a8a1fc2c96d21a33f9e1c45a95942398399e7d9ca4a7a1b2034f12a44a02ab0", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29e47d79fce6bf98afa6835441ddd04dc309e7c457b8974541c470599a46ddf6", "generation_seconds_batch": 14.130596464965492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.926964044570923, "target_z": 0.27929690060326195, "ce": 6.165581703186035, "genuineness": 4.030367851257324, "identity": 0.7506725788116455, "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/vn_VOLT_reg_high/6a8a1fc2c96d21a33f9e1c45a95942398399e7d9ca4a7a1b2034f12a44a02ab0.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "6adaa50391ce06a73148eb0c214498afcffce5fa2c68956fdbf5bbf540a7adea", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "877c5b91401e9e1be23f2a41cd4b96062ae6bcc895aacc2ff9ad0427b1f70542", "generation_seconds_batch": 21.653953721979633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5174179077148438, "target_z": -1.3437500579089485, "ce": 6.3641486167907715, "genuineness": 4.231201171875, "identity": 0.47788894176483154, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6adaa50391ce06a73148eb0c214498afcffce5fa2c68956fdbf5bbf540a7adea.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "6b8b8c28ad45c19b48328ad7edc7a62481b5f7e50ee14d9b9362b52e59ed2351", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f7948f001dcc84a2d1f640d47be766df263355e0359799f9b8665c369cd28a43", "generation_seconds_batch": 16.626343494979665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.427689552307129, "genuineness": 4.111956596374512, "identity": 0.6048179864883423, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6b8b8c28ad45c19b48328ad7edc7a62481b5f7e50ee14d9b9362b52e59ed2351.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "55929647289963d2af6c36c8f14189141232c0f125d9e193a393d2a2b4f26294", "generation_seconds_batch": 15.324904061038978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.043241500854492, "target_z": -0.738281133377812, "ce": 6.197352409362793, "genuineness": 4.595211505889893, "identity": 0.5950034856796265, "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/vn_VOLT_reg_high/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.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": "6bb69ef93ce0e8363e3125fe34bbf4da4e3f52e197367a08ac1db1b397eae5d4", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37d9cef2085026136eedaf8cf5c35f03357d72af4170b6e635e6da110b7ce30d", "generation_seconds_batch": 15.10900234093424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2671403884887695, "target_z": -0.4804687786863773, "ce": 6.062326908111572, "genuineness": 4.005263805389404, "identity": 0.6481257677078247, "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/vn_VOLT_reg_high/6bb69ef93ce0e8363e3125fe34bbf4da4e3f52e197367a08ac1db1b397eae5d4.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": "6bd7e699b5d3a38b7d51448ab33af017b1eefa0cf2bd90f8bdbf84a1eab32bc4", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "1ed934e4f3c39dca091a7ef4d72cfe7426acf132aa9ecfe55a30f9f4c0ef521f", "generation_seconds_batch": 14.714405186939985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9380767345428467, "target_z": -0.8593749731903016, "ce": 6.117925643920898, "genuineness": 4.494794845581055, "identity": 0.7912783026695251, "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/vn_VOLT_reg_high/6bd7e699b5d3a38b7d51448ab33af017b1eefa0cf2bd90f8bdbf84a1eab32bc4.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "6be31e256042d5f0902539d13a04c2b54ef411df4314e345243bd6d5a16d8a32", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1c4975abb411b68756316fdcd7fb5dac5d115ebcda45ecb3b241f014bbbed12e", "generation_seconds_batch": 15.191147006000392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6463295221328735, "target_z": -1.1953124876675387, "ce": 6.181467056274414, "genuineness": 4.262581825256348, "identity": 0.5257432460784912, "hypothesis": "I f 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/vn_VOLT_reg_high/6be31e256042d5f0902539d13a04c2b54ef411df4314e345243bd6d5a16d8a32.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "6bf1d7daaaf19f51fd537c3e9f01ee06d1d15a5810030c9504067da01b45f037", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "81c398c95172f36960616d8d8c7d6109ab19942311a58a635c73bcb930235faf", "generation_seconds_batch": 21.75434981903527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5581269264221191, "target_z": -1.296874934584336, "ce": 6.229123115539551, "genuineness": 4.375550270080566, "identity": 0.7274197936058044, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6bf1d7daaaf19f51fd537c3e9f01ee06d1d15a5810030c9504067da01b45f037.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "6c7bfc3acdd7f65546cffc4e4a3767ccfcaf2d4111c14b5f9e463a9493858d0e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "908adc7b54dfc4f2c0743395b7ca14e048f586ab73675e22949efe44b8e5042f", "generation_seconds_batch": 21.40997720195446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5174179077148438, "target_z": -1.3437500579089485, "ce": 6.332377910614014, "genuineness": 4.243753433227539, "identity": 0.4572373330593109, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6c7bfc3acdd7f65546cffc4e4a3767ccfcaf2d4111c14b5f9e463a9493858d0e.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "6ca69d15ff64e53776067be1216255dec1a67e6a19440fc13fe8b2dda5717422", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8a79a0bd6d291376c74702b48b5ce8425b0e7c2662aabc76d36b825cce90661b", "generation_seconds_batch": 21.75205057603307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9787856340408325, "target_z": -0.8124999871313447, "ce": 6.09409761428833, "genuineness": 4.074300289154053, "identity": 0.5133293867111206, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6ca69d15ff64e53776067be1216255dec1a67e6a19440fc13fe8b2dda5717422.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "6cbe73ca60ddf46afe01a910d44c11b6e92eebd68890995dac6f065b7b2a0ad7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5f6c2ae9f2ad074752a6375a08449056515f767288662e09ea78afef2d901606", "generation_seconds_batch": 21.323709243093617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.341773509979248, "target_z": -0.3945311441016913, "ce": 5.808161735534668, "genuineness": 4.093128204345703, "identity": 0.47456347942352295, "hypothesis": "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/vn_VOLT_reg_high/6cbe73ca60ddf46afe01a910d44c11b6e92eebd68890995dac6f065b7b2a0ad7.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": "6cd5ead1d2682c617fcfdf621f7019d59db0f1e1e1c762e77f4ad302f06f861b", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c8b139f0bdc3b5b07ed9350348b3b79d14ddf621d55c97e86c0a9228ff0d510a", "generation_seconds_batch": 13.876918382011354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8159499168395996, "target_z": -1.0000000686328279, "ce": 5.760505676269531, "genuineness": 4.068024158477783, "identity": 0.6025903820991516, "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/vn_VOLT_reg_high/6cd5ead1d2682c617fcfdf621f7019d59db0f1e1e1c762e77f4ad302f06f861b.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "6cf6c6ef90be3a271b15f4a87abe63ca7acf5aa8d74d4cfde1e8845f1909bcca", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2d475e9680d76ae5ffafc01e4d08e6ee4611639e0cfdcff80e0cbd46366faced", "generation_seconds_batch": 20.350313398987055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.598835825920105, "target_z": -1.249999948525379, "ce": 6.308549880981445, "genuineness": 4.20609712600708, "identity": 0.5599756836891174, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6cf6c6ef90be3a271b15f4a87abe63ca7acf5aa8d74d4cfde1e8845f1909bcca.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "6d11580fa4f2c73c03c5d41688c302a7959c807014e15bc83ee795a383731d62", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "be1fc445e0c4d9cae6dc0bd7752c858447b45b5114746f36d34c4e218fa00369", "generation_seconds_batch": 15.445601391955279, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.402076005935669, "target_z": -1.4765625412869354, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.5569512248039246, "hypothesis": "La porte 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/vn_VOLT_reg_high/6d11580fa4f2c73c03c5d41688c302a7959c807014e15bc83ee795a383731d62.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "6d11a6ce15bf496e27f75581414922473e78368cbab26dc40373df77f0dc3830", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "be84bfa37bf4c3e7b9fa74974e3ea2d2aed6024905dc5a43c9c3fecaf95c37d8", "generation_seconds_batch": 15.384285224950872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5716965198516846, "target_z": -1.2812499849865688, "ce": 6.41180419921875, "genuineness": 4.118232727050781, "identity": 0.28780597448349, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6d11a6ce15bf496e27f75581414922473e78368cbab26dc40373df77f0dc3830.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "6d234860d9d7be3169d58aea6bcbfabb031f17dcf4dd9a96e332d07693fc2924", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "477e0e2fc8c17b323eb57740ab60e6848f3804f15fcd2e658f36428ef4de95ac", "generation_seconds_batch": 19.566090628039092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6463295221328735, "target_z": -1.1953124876675387, "ce": 6.316492557525635, "genuineness": 4.105680465698242, "identity": 0.6172609329223633, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6d234860d9d7be3169d58aea6bcbfabb031f17dcf4dd9a96e332d07693fc2924.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "6d2828917c94a361ca74d80d31035dd6f998066bb7e2adf3060a6fbf9c598630", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "31f66d74eaae21a590b53777e3b97bc8864a5caad306215551468ff3e74bf476", "generation_seconds_batch": 15.357947338954546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.402076005935669, "target_z": -1.4765625412869354, "ce": 6.157639026641846, "genuineness": 4.6203155517578125, "identity": 0.5160440802574158, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6d2828917c94a361ca74d80d31035dd6f998066bb7e2adf3060a6fbf9c598630.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "6d2eac9803d8a8d83edab0fcc5601e7e00caa2e41ee96cf40dd50154b21277ba", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a62416fcc9d731b2cf72f3ec7a16ddeb43df744336f135e9a122a200bc93d9df", "generation_seconds_batch": 21.492408100049943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2867341041564941, "target_z": -1.6093750246649225, "ce": 6.149696350097656, "genuineness": 4.2249250411987305, "identity": 0.7586511373519897, "hypothesis": "La porte 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/vn_VOLT_reg_high/6d2eac9803d8a8d83edab0fcc5601e7e00caa2e41ee96cf40dd50154b21277ba.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "6da5b9b6651ecd885068f64de5ab210780c0508d5888e3346374044133036292", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4a2363d0d085863c6b6e526336bbd0f053609097037c609a3d1367fecb12d3f5", "generation_seconds_batch": 21.464936139062047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5581269264221191, "target_z": -1.296874934584336, "ce": 5.708878040313721, "genuineness": 3.848362922668457, "identity": 0.3049449324607849, "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/vn_VOLT_reg_high/6da5b9b6651ecd885068f64de5ab210780c0508d5888e3346374044133036292.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "6db51c54729f40c7fd8697b9e48ebf1a769bc70d470bcee9983745ce281527cb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6165506d28fbe41aa8f91716b1a0e8ef4544afff5572315c4a65cb6700300ad8", "generation_seconds_batch": 19.82850195397623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4427849054336548, "target_z": -1.4296875552279786, "ce": 6.09409761428833, "genuineness": 4.193545341491699, "identity": 0.6905902028083801, "hypothesis": "La porte 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/vn_VOLT_reg_high/6db51c54729f40c7fd8697b9e48ebf1a769bc70d470bcee9983745ce281527cb.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "6e2b89a58a55ea2e3ba1f3acb085386b1e988ed03659f3ef1091524f83b9c555", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "71dc1111e8ad2ba5d08a1ca4ba19d9b97cd123f14d4d625fde2de721187dccd4", "generation_seconds_batch": 20.190976098063402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5445572137832642, "target_z": -1.3125000214477587, "ce": 6.038498878479004, "genuineness": 4.281409740447998, "identity": 0.6406632661819458, "hypothesis": "La porte 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/vn_VOLT_reg_high/6e2b89a58a55ea2e3ba1f3acb085386b1e988ed03659f3ef1091524f83b9c555.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": "6e504a9e445c07c84bbf967d148f37e7891b922e455a492273baffbab7ffe4b0", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "28fabd1262948cfe906fcf337234502d456537e1ef90b9cd2c60964b35e39060", "generation_seconds_batch": 13.596925228950568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.418102741241455, "target_z": -0.30664049376652636, "ce": 5.935244083404541, "genuineness": 3.961331605911255, "identity": 0.24992740154266357, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weg gaat.", "wer": 0.09090909090909091, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6e504a9e445c07c84bbf967d148f37e7891b922e455a492273baffbab7ffe4b0.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "6e60cbae4ae16c3966f3c4f531fff659bfed676ce41170655f6c473559da2562", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b9a21ad201f5c3c0fe4f075e3bdae5c558ab42e20f6c2e3d997214a077c46067", "generation_seconds_batch": 21.75434981903527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8023803234100342, "target_z": -1.0156250182305948, "ce": 6.149696350097656, "genuineness": 4.607763767242432, "identity": 0.55275958776474, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6e60cbae4ae16c3966f3c4f531fff659bfed676ce41170655f6c473559da2562.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": "6e878ea6f5d61a4ac9bd34d7e2897a2ad5d326dfa3c968677ffbd17680aa9cf0", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "83f2e246a9715da585b38c030b4e25b261136e71c134dff01f652041880f1cf3", "generation_seconds_batch": 22.030410493025556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6056206226348877, "target_z": -1.2421874737264955, "ce": 5.911416053771973, "genuineness": 4.055472373962402, "identity": 0.4828764796257019, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6e878ea6f5d61a4ac9bd34d7e2897a2ad5d326dfa3c968677ffbd17680aa9cf0.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "6e8fb40d7ff3776aac0150f594acd9c3eb2cc322653aa81bdc9a6a240c141b32", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b47e6e9d1006bb02c5109df6217f3ff375142598ef7e4a45ef32ae745fc73496", "generation_seconds_batch": 19.87495442200452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.033064126968384, "target_z": -0.7500000514746209, "ce": 6.09409761428833, "genuineness": 4.595211505889893, "identity": 0.485881507396698, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6e8fb40d7ff3776aac0150f594acd9c3eb2cc322653aa81bdc9a6a240c141b32.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "6e9865eaf991b2fa634f31351dcf2c1be96e9e4354c734721f8f45e9340e7e81", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "55b3ffeac9f3678a9c89d93402604641914a0fbcffad6301cb06e0a01176eccf", "generation_seconds_batch": 15.112159300944768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9211146831512451, "target_z": -0.8789062288203383, "ce": 6.2767791748046875, "genuineness": 4.243753433227539, "identity": 0.6829570531845093, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6e9865eaf991b2fa634f31351dcf2c1be96e9e4354c734721f8f45e9340e7e81.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": "6eeec1cd9413a0d28b3d0ada2f5ce281087db3af7f80762c7989db70923eaab0", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I wrote the number on the envelope.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "01728190818df797440132af584e7da2296d379edd6874cf95e375905a8b2881", "generation_seconds_batch": 15.368403851985931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1823301315307617, "target_z": -0.5781250568365606, "ce": 6.316492557525635, "genuineness": 3.8546390533447266, "identity": 0.3856431543827057, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6eeec1cd9413a0d28b3d0ada2f5ce281087db3af7f80762c7989db70923eaab0.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "6ef6a55bc9f006a4bc7a09ef496bb908ef2d247cbd39e687b02312612e4bf448", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d02844b77739c389f409cd00e4ab3de1eb7b57b4034b0e9aa06d4c7c26f527eb", "generation_seconds_batch": 23.165007681935094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.094127655029297, "target_z": -0.679687366487702, "ce": 6.340320587158203, "genuineness": 4.532451152801514, "identity": 0.6397347450256348, "hypothesis": "Die Tür ist noch. Ich habe 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/vn_VOLT_reg_high/6ef6a55bc9f006a4bc7a09ef496bb908ef2d247cbd39e687b02312612e4bf448.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "6f39c6ea5269f5666acb5dd7e1949f40af9250057ff79d5893a3ff4c3e4625c3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f129037ae542fe80bdd13f075fc6d1e0967852213461182592e646893201ba41", "generation_seconds_batch": 21.72193162399344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7573435306549072, "target_z": 0.08398434430289534, "ce": 6.0305562019348145, "genuineness": 4.030367851257324, "identity": 0.6057455539703369, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6f39c6ea5269f5666acb5dd7e1949f40af9250057ff79d5893a3ff4c3e4625c3.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "6f71cf1df3676767b6b78d4d92fd91e34df48744f4407f5924414cd978ca624b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "177e6374fcba72c6c86c2173e8a34b693d1325b68885e986054dcc2c411e140d", "generation_seconds_batch": 20.242440949077718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.116939067840576, "target_z": 0.4980470185659349, "ce": 5.621508598327637, "genuineness": 3.503180742263794, "identity": 0.6672871112823486, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6f71cf1df3676767b6b78d4d92fd91e34df48744f4407f5924414cd978ca624b.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "6f909bbd4cfe957024fd50d969b4b0ed2cceb031c553f40fe5958f035ba7e56f", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "daf54cda181858dba20500662d84666a0dd489c02d2a1c1e34f4d00e056178e9", "generation_seconds_batch": 16.28369496704545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6802536249160767, "target_z": -1.1562499764074654, "ce": 6.38797664642334, "genuineness": 4.432034492492676, "identity": 0.623542308807373, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6f909bbd4cfe957024fd50d969b4b0ed2cceb031c553f40fe5958f035ba7e56f.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "6fbed6372e561a75fbd4d52cd0e5d40fad0c84b4146ba9e7abdf410a6a530e47", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "007909003f4359d849d8234fd748c729648bb774d9ea9d8be453a386430dc253", "generation_seconds_batch": 21.622066995943896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3289644718170166, "target_z": 0.7421874394100816, "ce": 5.458683967590332, "genuineness": 3.653805732727051, "identity": 0.4317590594291687, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/6fbed6372e561a75fbd4d52cd0e5d40fad0c84b4146ba9e7abdf410a6a530e47.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "710fba8745e16e2f3b04f54818e0b59364198a2130cf545fc04be40bf2fab09d", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b0a268f172d2835d182a747c91fd774d75eaa4b81b2701776597353ab0387513", "generation_seconds_batch": 16.02544629503973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3003038167953491, "target_z": -1.5937499378014996, "ce": 6.213237762451172, "genuineness": 4.469690799713135, "identity": 0.5268456935882568, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/710fba8745e16e2f3b04f54818e0b59364198a2130cf545fc04be40bf2fab09d.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "7113e9c25b940b847c10efcfa4b76f20ad9e0010cf6be64443b07bb2e3684d7f", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5e3e84bda16f17624dd143eea0121b910f1ded7d55582a7a5e6d100ba33f665e", "generation_seconds_batch": 15.255104401963763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.693823218345642, "target_z": -1.1406250268096985, "ce": 6.117925643920898, "genuineness": 4.331617832183838, "identity": 0.5498029589653015, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7113e9c25b940b847c10efcfa4b76f20ad9e0010cf6be64443b07bb2e3684d7f.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "71495d722f8a0ac2be96551ae0de66b3f427809ea628c1e225685125dc4c5f8b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c81284b3425ceb31d24e659ec99a0cf492df0e10741a04643d862ec9fc55ffef", "generation_seconds_batch": 20.098065205966122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9720008373260498, "target_z": -0.8203124619302283, "ce": 6.221180438995361, "genuineness": 4.356721878051758, "identity": 0.6326247453689575, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/71495d722f8a0ac2be96551ae0de66b3f427809ea628c1e225685125dc4c5f8b.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "727804e7c0b1dd72393d96a9592a5c7aad2d0859b64d30a90cafd2dd812fb269", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "05e32cfedd4a40b16881e73a188a60d7630b45c9e60e4b16e9202e3a5af50240", "generation_seconds_batch": 15.648692439077422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.24500846862793, "genuineness": 4.13078498840332, "identity": 0.6249951124191284, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/727804e7c0b1dd72393d96a9592a5c7aad2d0859b64d30a90cafd2dd812fb269.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "730c6b9702855b1fb130f952487498e61a7ed3ef31dcf8ba1498d6b302243e22", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5a76bec5eff6d6b75716db691b68fcb890b9d190123b4dc86d960a4362f35b86", "generation_seconds_batch": 15.51970797299873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.673468828201294, "target_z": -1.1640624512063489, "ce": 5.998785495758057, "genuineness": 4.419482707977295, "identity": 0.7575501203536987, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/730c6b9702855b1fb130f952487498e61a7ed3ef31dcf8ba1498d6b302243e22.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "73201ccb427838c520bd21412556682c9578ee33f55dbea42527c2954c2d1d01", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7cf5912746d526213cfc3c37bae7d101b1e924a353d8903481bec6ca909e5d7", "generation_seconds_batch": 21.784027372021228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.02195143699646, "target_z": 0.38867182231894265, "ce": 5.629451274871826, "genuineness": 3.6475296020507812, "identity": 0.2921580672264099, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude ramen. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/73201ccb427838c520bd21412556682c9578ee33f55dbea42527c2954c2d1d01.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "732720b0c1397c73f0ecc2035c2eb130c48ee956f246ad86c4a3fb53f1b66719", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "92ed2f4cfd6648740ecc65ec7c39aa117504e65f6cbeffa2061866fec0aa0b0c", "generation_seconds_batch": 14.476241000927985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4699242115020752, "target_z": -1.3984375187667888, "ce": 6.205295085906982, "genuineness": 3.948779582977295, "identity": 0.6048620343208313, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/732720b0c1397c73f0ecc2035c2eb130c48ee956f246ad86c4a3fb53f1b66719.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "733afd349368f10f6d3233e668a282cf8470609843ef40c75a79e959d3325d91", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1f01decb1ef4cc549eaf1f38d8ce4cbc0025b4acd9c0e4c07491f6ffad1d91ba", "generation_seconds_batch": 21.09063850506209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.659899115562439, "target_z": -1.1796875380697718, "ce": 6.078212261199951, "genuineness": 4.457139015197754, "identity": 0.45027267932891846, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/733afd349368f10f6d3233e668a282cf8470609843ef40c75a79e959d3325d91.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": "734d55eea2709f6e1315e5bf2e60b3fef7c511e5297221c7d3c1a77e5aec42fc", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30cbb4908a550c12171eaecccf550625c4df511525ab7192bdcde0c99b91ba63", "generation_seconds_batch": 13.569872471038252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.586026906967163, "target_z": -0.11328122774795034, "ce": 6.0146708488464355, "genuineness": 4.20609712600708, "identity": 0.5686365365982056, "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/vn_VOLT_reg_high/734d55eea2709f6e1315e5bf2e60b3fef7c511e5297221c7d3c1a77e5aec42fc.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": "739246713616e9a228084acab8c744aa3462d1f79f96e8b812f6ea6bed82b5a3", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b48817429c796ddb6e2db55c064c4be9877efcbc15b59863945489e034c7c2f2", "generation_seconds_batch": 13.673604854033329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8159499168395996, "target_z": -1.0000000686328279, "ce": 6.157639026641846, "genuineness": 3.9173994064331055, "identity": 0.7540338635444641, "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/vn_VOLT_reg_high/739246713616e9a228084acab8c744aa3462d1f79f96e8b812f6ea6bed82b5a3.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": "73f0eca86959234df6c50f7d8ebbddab6cbbe123cd428544cc9c0dab6d59a18f", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "885787477b7a00cea0721ecc89b6029b7439ea798bc0a786e99d984ceb24a28d", "generation_seconds_batch": 21.01419704791624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.104304790496826, "target_z": -0.6679687229222047, "ce": 6.062326908111572, "genuineness": 4.143336772918701, "identity": 0.5687676668167114, "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/vn_VOLT_reg_high/73f0eca86959234df6c50f7d8ebbddab6cbbe123cd428544cc9c0dab6d59a18f.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "73f4a0ab443dc5a8495592a25113fa9a4214e6b8b2378e8c640e4689fb9c23ff", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "379a6f4ba95e79481d6903eeeeeef7aef75f646f233faa65e5cd610e164c208d", "generation_seconds_batch": 22.247288572019897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.436000108718872, "target_z": -1.437500030026862, "ce": 6.3641486167907715, "genuineness": 4.356721878051758, "identity": 0.34124016761779785, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/73f4a0ab443dc5a8495592a25113fa9a4214e6b8b2378e8c640e4689fb9c23ff.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": "743a62e38caf82163652a2049b7471cfe8459699ae599e2040b9550564e6dd7c", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "37503d0edb8db610d1e03f45252b44ce96518897ccf24d1fe2af389f93ea5307", "generation_seconds_batch": 15.553710992098786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8887994289398193, "target_z": 0.23535157543567947, "ce": 5.935244083404541, "genuineness": 4.030367851257324, "identity": 0.5150517225265503, "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/vn_VOLT_reg_high/743a62e38caf82163652a2049b7471cfe8459699ae599e2040b9550564e6dd7c.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "74c295ca3aeff8bc3dfdec328ea486212cec1862cf8bd6d3ddddd7a0a216b28a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5d36fea1ae62ec521122d154ebf69f5f72c4f886d06c43c94a2eed98f54247c3", "generation_seconds_batch": 23.471899840049446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.58526611328125, "target_z": -1.2656250353888019, "ce": 6.332377910614014, "genuineness": 4.432034492492676, "identity": 0.4382605254650116, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/74c295ca3aeff8bc3dfdec328ea486212cec1862cf8bd6d3ddddd7a0a216b28a.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "7538658864fe9f461f64a0edc058c9aca999660de755c6d69962e02950b4586d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2a0abf3d1eedfc535e509683d134371a1ac1acae244804d686e66151252989a7", "generation_seconds_batch": 21.05814796197228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0873427391052246, "target_z": -0.6874999785522413, "ce": 6.022613525390625, "genuineness": 3.898571252822876, "identity": 0.7308415770530701, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7538658864fe9f461f64a0edc058c9aca999660de755c6d69962e02950b4586d.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "7574e64a5b74f8ec5a919d6703ab9d381a510324c1d59ded1b0baf6fccbfceda", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b66313b73f831fed59469e3b06e1f20b2e6704d69788b9b41a9aef2d13aebc02", "generation_seconds_batch": 20.988095427979715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0568110942840576, "target_z": -0.7226561837800449, "ce": 6.038498878479004, "genuineness": 4.137060642242432, "identity": 0.5987439751625061, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7574e64a5b74f8ec5a919d6703ab9d381a510324c1d59ded1b0baf6fccbfceda.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "7621a25fde115b75e36110cf7f438e79225b2c3e5234108b7eb52045eb50ae26", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "08a0c98fa7e2d67256978e62c4846b7fda53697c85a132ef85639d92977fee6b", "generation_seconds_batch": 20.858146449900232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3817216157913208, "target_z": -1.499999965683586, "ce": 6.23706579208374, "genuineness": 4.068024158477783, "identity": 0.4264979362487793, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7621a25fde115b75e36110cf7f438e79225b2c3e5234108b7eb52045eb50ae26.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "763a5059290334a3d78263172b8cb427c45718f314081d78a4d418eb45f44a05", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9cb3f57cdc8b9197b908db7c7e348f4fb7c5607c0c4749c51d019cb8518d073e", "generation_seconds_batch": 15.793302399921231, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.117925643920898, "genuineness": 4.086852550506592, "identity": 0.7724335789680481, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/763a5059290334a3d78263172b8cb427c45718f314081d78a4d418eb45f44a05.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "7641dfed56fb52b4086d8391bab41ee26ed0894662f3a9fdb8c94a52a15e0bf7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f2847037b86da0ff5626aae19a51271ae7af8706ec1c3373b430e7580a577383", "generation_seconds_batch": 21.05031862691976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.673468828201294, "target_z": -1.1640624512063489, "ce": 6.348263263702393, "genuineness": 4.20609712600708, "identity": 0.5626336932182312, "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/vn_VOLT_reg_high/7641dfed56fb52b4086d8391bab41ee26ed0894662f3a9fdb8c94a52a15e0bf7.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "76432b03a8068bb1ae19308842577fdc9d34a3ff39f0444a824784e07e5c1ea6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "56f602f055eb4b3b2a5af348a7d115a758dc60564effdcd3dc1cae24632c23de", "generation_seconds_batch": 21.880549073102884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5080015659332275, "target_z": -0.20312489383359436, "ce": 5.254160404205322, "genuineness": 3.6663577556610107, "identity": 0.4201447367668152, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "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/vn_VOLT_reg_high/76432b03a8068bb1ae19308842577fdc9d34a3ff39f0444a824784e07e5c1ea6.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "76550fdc929a3e4d9d09685c69a10df217ce66c58cff8d73c0930b9d8c3dd948", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "24835df05b8aa07de6f2eaf9b7491f668402e832add15ee7224aa13ca2b6db35", "generation_seconds_batch": 20.143000334966928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3138734102249146, "target_z": -1.5781249882037327, "ce": 6.0305562019348145, "genuineness": 4.074300289154053, "identity": 0.4011145234107971, "hypothesis": "La porte 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/vn_VOLT_reg_high/76550fdc929a3e4d9d09685c69a10df217ce66c58cff8d73c0930b9d8c3dd948.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "7668fcdff6a479b0917a57057752e941e5ff2391584cdbd263b228ea89dfc810", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "52c8e8e5aedea48aa1264fea6e3011c53c514930271d8b22b8313682d05c90c4", "generation_seconds_batch": 20.640695137903094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2128617763519287, "target_z": -0.542968851608757, "ce": 6.141753673553467, "genuineness": 3.8044304847717285, "identity": 0.48217758536338806, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7668fcdff6a479b0917a57057752e941e5ff2391584cdbd263b228ea89dfc810.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "769cd769013bda4cd3e0ed2469b7247901944fccd863d13ab8bbfa00366aeece", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "e7d4f183355ff612cd3288bddadc4e9cd7ad95e9a731df57b5e5f13862d326c1", "generation_seconds_batch": 22.612461411044933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.436760902404785, "target_z": -0.2851562223860106, "ce": 6.149696350097656, "genuineness": 4.300237655639648, "identity": 0.44628652930259705, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/769cd769013bda4cd3e0ed2469b7247901944fccd863d13ab8bbfa00366aeece.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": "772d24ad974366f9c553a36fd5eb92503ad722cf39ba3f9daad3cc30302455a4", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2b06aa0b228de7dc1ed64fbfcd76a1535fa02122fecca32cea87a276a136cff3", "generation_seconds_batch": 20.559555140091106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.625039577484131, "target_z": -0.06835939470512832, "ce": 5.8875885009765625, "genuineness": 4.18726921081543, "identity": 0.6235971450805664, "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/vn_VOLT_reg_high/772d24ad974366f9c553a36fd5eb92503ad722cf39ba3f9daad3cc30302455a4.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": "77513636335b66c222706ba50d2b55e55f43c0583ef8451e41a6ee3e59201419", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Your message arrived after I had left.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea463ddc13b1172934c49443909925ffa490fa9ed7a3699a155c438133f682f8", "generation_seconds_batch": 22.188285840908065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.643697738647461, "target_z": -0.04687512332461262, "ce": 5.879645347595215, "genuineness": 4.093128204345703, "identity": 0.3598496615886688, "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/vn_VOLT_reg_high/77513636335b66c222706ba50d2b55e55f43c0583ef8451e41a6ee3e59201419.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "611a239b7ad0291739fdcaddb0a087469f4a39f39b266b5ae21ed81cac0f14a4", "generation_seconds_batch": 16.259736391948536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5920509099960327, "target_z": -1.2578125605899184, "ce": 6.117925643920898, "genuineness": 4.607763767242432, "identity": 0.6393882632255554, "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/vn_VOLT_reg_high/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "77b07d66bd6baa1637e5ea576aa2e94eb6fe01fafc1797c5561c2aacb2e0b88d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2a2032b4d3cc4b022faccb569e8ca10eab697eb1a022cb764b39e3b0e1796ab5", "generation_seconds_batch": 20.40473544294946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.734532117843628, "target_z": -1.0937500407507417, "ce": 6.252951145172119, "genuineness": 3.9425034523010254, "identity": 0.516900360584259, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/77b07d66bd6baa1637e5ea576aa2e94eb6fe01fafc1797c5561c2aacb2e0b88d.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "77ca84e3f4b3ebad1e2ce7a8630efc64cae673b76d11644df360079f354e882b", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2f83f1c776ef01acd181d5903b9bf3a15de34f8df8c69dccd11912bddca1d1e4", "generation_seconds_batch": 15.753814158961177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4631394147872925, "target_z": -1.4062499935656725, "ce": 6.038498878479004, "genuineness": 3.998987913131714, "identity": 0.6420767307281494, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/77ca84e3f4b3ebad1e2ce7a8630efc64cae673b76d11644df360079f354e882b.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "78414ab1706e791859252a4e807724a06fc69922bcbd69fba89222d534db88df", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d5ca62b6c02ec6c026dabe13a914c40602a4b9bc3c20096eda2a4704153ed961", "generation_seconds_batch": 14.714047441957518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3221797943115234, "target_z": 0.734375101876854, "ce": 5.089349746704102, "genuineness": 3.6914620399475098, "identity": 0.5281317830085754, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo.", "wer": 0.13333333333333333, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/78414ab1706e791859252a4e807724a06fc69922bcbd69fba89222d534db88df.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "785c093c131b81df5bca84438c1d3663db23b65fbcb9cf9f69e04bd450bbb699", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "44c312da89147d279cf54cb147429c6af7eedff049b7ee6517a530a5407fbc70", "generation_seconds_batch": 21.30428825400304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8981285095214844, "target_z": 0.24609371112593734, "ce": 6.046441555023193, "genuineness": 4.218649387359619, "identity": 0.5035301446914673, "hypothesis": "La porte 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/vn_VOLT_reg_high/785c093c131b81df5bca84438c1d3663db23b65fbcb9cf9f69e04bd450bbb699.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": "78f2f448c8b9764b28c5e5b6fd9231eef0666f2607e1286cf771293be713997c", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c159ca193f02bdab2a2d336b173e5337a3f573a8401cbe1e35d274785307d47c", "generation_seconds_batch": 21.537026252946816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8837108612060547, "target_z": 0.2294922536529308, "ce": 5.792276382446289, "genuineness": 3.3745219707489014, "identity": 0.5264739394187927, "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/vn_VOLT_reg_high/78f2f448c8b9764b28c5e5b6fd9231eef0666f2607e1286cf771293be713997c.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "7937459f75e55dd161c90e1d84504f2f36cabce610503983fe31ebc18a005fa0", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0954bee5423dd72d4dd92d08b7e029cf49c46f18d473ac5d0840308a32909ced", "generation_seconds_batch": 16.626343494979665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.38003396987915, "genuineness": 4.287685871124268, "identity": 0.4677954316139221, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7937459f75e55dd161c90e1d84504f2f36cabce610503983fe31ebc18a005fa0.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "54dda5f4d28f7e7c0de6286f801b426c580730f3edc5f268421e19c6b44cf122", "generation_seconds_batch": 15.909355314914137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9448615312576294, "target_z": -0.8515624983914181, "ce": 6.141753673553467, "genuineness": 4.519899368286133, "identity": 0.5805225372314453, "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/vn_VOLT_reg_high/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "79dad992c1144a2ba81aab878aac3f1ece79ecc6ebe0c44a22c0f16b5d3c3136", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3f110bd7731a6967b66cd65347af0a5feffb924cc9510e0f38ecf3f0acea87ba", "generation_seconds_batch": 16.923748617060483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.673468828201294, "target_z": -1.1640624512063489, "ce": 6.316492557525635, "genuineness": 4.400654315948486, "identity": 0.4047867953777313, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/79dad992c1144a2ba81aab878aac3f1ece79ecc6ebe0c44a22c0f16b5d3c3136.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "7a1fb6d23da382cf4815d779bd3abe711470a472c2c87a8869452312f6c874bc", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8e5bb0b9865ed956956b94d4c9b1e91b8e507a917444a78c648d0bd3bf550f99", "generation_seconds_batch": 21.568163929972798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1306833028793335, "target_z": -1.7890624941018665, "ce": 6.133810997009277, "genuineness": 4.319066047668457, "identity": 0.8545979261398315, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7a1fb6d23da382cf4815d779bd3abe711470a472c2c87a8869452312f6c874bc.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "7a2a4e1faed8da7e7b4f7a10a279d1270c8ed2424a2a620f03f075ee6bfb5b2f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "725b123a76765fad9ef5f4cbee2c5a917d6c41cbe2404ff42f71d86a0c9c68c4", "generation_seconds_batch": 21.027458452037536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8736209869384766, "target_z": -0.9335936896781786, "ce": 6.38003396987915, "genuineness": 4.306513786315918, "identity": 0.30006855726242065, "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/vn_VOLT_reg_high/7a2a4e1faed8da7e7b4f7a10a279d1270c8ed2424a2a620f03f075ee6bfb5b2f.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "7a3f8ce425415b8afc8ee3b645126b80042e3ab37fabd84d88baf381d5d0b7ac", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9159c28987a5a2dec3d2570907156414cb413fdb16709df7dcfcc6def1c3fa28", "generation_seconds_batch": 16.46181519597303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0153414011001587, "target_z": -1.9218749774798534, "ce": 6.181467056274414, "genuineness": 3.7416701316833496, "identity": 0.12325315922498703, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7a3f8ce425415b8afc8ee3b645126b80042e3ab37fabd84d88baf381d5d0b7ac.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "7ac3ba94fba636f3513ddfb608da5ed63a1467575df3159e2e5f17e479b79856", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "57cf03f7747a7df9cb909fd22a4530684ad31da78cec988d986570604ee9ef2e", "generation_seconds_batch": 17.359654592932202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.332377910614014, "genuineness": 4.093128204345703, "identity": 0.4924522638320923, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7ac3ba94fba636f3513ddfb608da5ed63a1467575df3159e2e5f17e479b79856.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "7c4d08862302a4e6c4c9e1cc10d4638da4d1d8686104a1f369a5cc348593240d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c6aa3cb1253719c9813c966171eada737b33fad7b48103a00b8cfde59bff161a", "generation_seconds_batch": 21.760832691099495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5300521850585938, "target_z": -0.177734316420809, "ce": 5.959072113037109, "genuineness": 3.8546390533447266, "identity": 0.5879738926887512, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7c4d08862302a4e6c4c9e1cc10d4638da4d1d8686104a1f369a5cc348593240d.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "7c6fc1972bcec55d3f589c8b1de1b0ba2209a937658e451411fc62b9ee6732b5", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "267a506d239cce0771adb8e852cb3487167ca7c60eaea0376c3b77f45ca51d8b", "generation_seconds_batch": 15.670838841004297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.280709981918335, "target_z": -0.46484382908861027, "ce": 5.959072113037109, "genuineness": 4.111956596374512, "identity": 0.5104324817657471, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7c6fc1972bcec55d3f589c8b1de1b0ba2209a937658e451411fc62b9ee6732b5.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "7c8237fa325148c8c589ccca758b56edc7fbaa27f1b47fc7d01ea86305fecd7c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "67f4f3f636185428e23aa2295c594b5e43a8a34c8cfb3fb968d3342d891f0a6f", "generation_seconds_batch": 22.08692156802863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.734532117843628, "target_z": -1.0937500407507417, "ce": 6.229123115539551, "genuineness": 4.256305694580078, "identity": 0.5600094795227051, "hypothesis": "De deur staat er nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7c8237fa325148c8c589ccca758b56edc7fbaa27f1b47fc7d01ea86305fecd7c.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": "7cbc63b36ffefce3b9c98cd86d0b116724becb2f6a785664906ec945d89061fd", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The road turns left behind the bridge.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c98007a4ffac08f539441803706fbf01c73e45038516713c3a665a607b608a7", "generation_seconds_batch": 14.553001404041424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.066988229751587, "target_z": -0.7109375402145476, "ce": 6.078212261199951, "genuineness": 3.8922953605651855, "identity": 0.23448079824447632, "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/vn_VOLT_reg_high/7cbc63b36ffefce3b9c98cd86d0b116724becb2f6a785664906ec945d89061fd.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "7d0d8b09c0a2d957de7f217736e2f9835c01b32201e856d6915576c4f08afd65", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c84c6dd263753cae1f5dc2bed19129f0d3ef70eb261dd2796d69156ecd0d1f69", "generation_seconds_batch": 15.698437181999907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5920509099960327, "target_z": -1.2578125605899184, "ce": 6.070269584655762, "genuineness": 3.860914945602417, "identity": 0.3178924024105072, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7d0d8b09c0a2d957de7f217736e2f9835c01b32201e856d6915576c4f08afd65.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "7d1ebd74c6af8fb94768abb0d680f6f405650554346c59ccf4c4bae969d712f9", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3736a869591a9b10025dc2aa302f252c8a5e4ebf81eb400c7a8b88106dd24f9f", "generation_seconds_batch": 22.153891149908304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0873427391052246, "target_z": -0.6874999785522413, "ce": 5.935244083404541, "genuineness": 4.068024158477783, "identity": 0.6316065788269043, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7d1ebd74c6af8fb94768abb0d680f6f405650554346c59ccf4c4bae969d712f9.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "7d54ec77a00c8f87800087d9177dc128418e3b49276cc80b4fb0c471362c1291", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ef305df4c1e51334ce86d7faeacba3c5d68b04b0c007bba490d742c258b81f0a", "generation_seconds_batch": 16.551221503061242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.673468828201294, "target_z": -1.1640624512063489, "ce": 6.078212261199951, "genuineness": 4.381826400756836, "identity": 0.6893125772476196, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7d54ec77a00c8f87800087d9177dc128418e3b49276cc80b4fb0c471362c1291.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "7d559071c501074717504d46f1d92167b558a3d776978401d0d3a511cc83e8c5", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "efd6540695bd822941549fb3fc2a619ad559d2a8069b45d67c69853f51f80291", "generation_seconds_batch": 21.72804333898239, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7141776084899902, "target_z": -1.1171876024130478, "ce": 6.062326908111572, "genuineness": 4.494794845581055, "identity": 0.37298622727394104, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7d559071c501074717504d46f1d92167b558a3d776978401d0d3a511cc83e8c5.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "7e486e210e0a9b856be354f259717b440f46d04314f0a8b2f5f528756cd9a56e", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "efc477025a2f5873b73701500e6c35c0f3ae6e54481aa8a6d8dde052f5a10847", "generation_seconds_batch": 16.1133835259825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3003038167953491, "target_z": -1.5937499378014996, "ce": 6.221180438995361, "genuineness": 4.432034492492676, "identity": 0.7656645774841309, "hypothesis": "They trouble the petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contiens.", "wer": 0.47368421052631576, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7e486e210e0a9b856be354f259717b440f46d04314f0a8b2f5f528756cd9a56e.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "7ead1e2c5ebb0b3c1cf889108f7959db92792f3ebd8705975943d65c12e0d097", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8cfe0381108de6b7759aab85a6b4370fdb8e502bce8ded8f30cc740be3e51051", "generation_seconds_batch": 15.571971231023781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8804056644439697, "target_z": -0.9257813521449508, "ce": 6.141753673553467, "genuineness": 4.419482707977295, "identity": 0.6138432621955872, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7ead1e2c5ebb0b3c1cf889108f7959db92792f3ebd8705975943d65c12e0d097.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "7f0708ac9011ffe94ffbe93ec3acbd2ba1b8dcff0f18784258a799d61789b352", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "084f291d6ffb5c48f7bf76a9bf2f6fcbd45a8ddc4bae69a2ff5e736612de023e", "generation_seconds_batch": 15.407074267044663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.178176999092102, "target_z": -1.734375033244026, "ce": 6.221180438995361, "genuineness": 3.835810661315918, "identity": 0.2132345288991928, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7f0708ac9011ffe94ffbe93ec3acbd2ba1b8dcff0f18784258a799d61789b352.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": "7f2f00452b4d4e9723026f0a2de7d86e883ada37d9893b113ae2530f8b120633", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "16eeed8dc61c35b47990538dc94e377d99808d08c4a0a1d9e092cec014d56b31", "generation_seconds_batch": 16.066876917961054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1687605381011963, "target_z": -0.5937500064343276, "ce": 6.268836498260498, "genuineness": 4.174716949462891, "identity": 0.6952286958694458, "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/vn_VOLT_reg_high/7f2f00452b4d4e9723026f0a2de7d86e883ada37d9893b113ae2530f8b120633.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "9930ead0b929522baf226ddf73b3887a2f4889c8ecab81cf36cc8beaf333e9b6", "generation_seconds_batch": 14.993324465001933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2935189008712769, "target_z": -1.601562549866039, "ce": 6.403861999511719, "genuineness": 4.281409740447998, "identity": 0.3903053402900696, "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/vn_VOLT_reg_high/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "7fa2116a95cd9497baf733236483453fd0a8aa1b16b9a77c21d6e631c5230489", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "62e3e85a780664e9588fc5fb2f3671e64668784f939dead6bdf90a277caffdd2", "generation_seconds_batch": 21.125218773959205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.854027271270752, "target_z": 0.19531255630036662, "ce": 5.831989288330078, "genuineness": 4.042920112609863, "identity": 0.6071553826332092, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We pouvons regarder ensemble what it contient.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7fa2116a95cd9497baf733236483453fd0a8aa1b16b9a77c21d6e631c5230489.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "7ff0e44a5dd8a36a83b63339cc80ee93fcb0349f3d3dd0fd322b2de80829e73d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9d6f7b11fdc871247f1bee15e20038ddaf82e976c582432ce0de3adc0e2c4f37", "generation_seconds_batch": 15.041157491970807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6666839122772217, "target_z": -1.1718750632708883, "ce": 6.0305562019348145, "genuineness": 4.281409740447998, "identity": 0.4271479845046997, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/7ff0e44a5dd8a36a83b63339cc80ee93fcb0349f3d3dd0fd322b2de80829e73d.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "803aa74f26f793b32194fc6f505f05de7e5623b0d9fc7fcfb45c7b0e0c4cdb4a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1d2b2cd89c0fdf19bf176573fa561e8caf24fda8f15ec5f8193f9d136406f1d8", "generation_seconds_batch": 24.13415482104756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8363044261932373, "target_z": -0.9765625069705216, "ce": 6.252951145172119, "genuineness": 4.168440818786621, "identity": 0.3193642497062683, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/803aa74f26f793b32194fc6f505f05de7e5623b0d9fc7fcfb45c7b0e0c4cdb4a.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "8048736bab19edbfa5c5103e80cc67b43435ad633bf2ebd6c0538c5e42d8d19c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "338a6db547973f75ede7ed10cc68934b979cf3c7eb10ccd3368e370ae6366e24", "generation_seconds_batch": 16.429961288929917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.403597593307495, "target_z": 0.8281250739947675, "ce": 5.617537498474121, "genuineness": 3.4686625003814697, "identity": 0.5094596147537231, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8048736bab19edbfa5c5103e80cc67b43435ad633bf2ebd6c0538c5e42d8d19c.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": "804a5c4e72ff167429848e8a25479747d00b90ddc42f1690b71f795c45df97ec", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "8fdd88f883dc8eff2df662207607f3d1fbc65d78ac5d909fdc7d55db5ecb9b4a", "generation_seconds_batch": 15.706233208067715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5258116722106934, "target_z": -0.18261713032831817, "ce": 6.268836498260498, "genuineness": 4.118232727050781, "identity": 0.6541421413421631, "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/vn_VOLT_reg_high/804a5c4e72ff167429848e8a25479747d00b90ddc42f1690b71f795c45df97ec.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "80647ec14798796bff773cb32a0e21d0c8078adf328bc179262446ccef89f8fe", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "89e70b76b351bb8c227afa71cfa161ee80b80e182ab8b095c355421efc162ed0", "generation_seconds_batch": 15.056643356918357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7209625244140625, "target_z": -1.1093749903485086, "ce": 6.268836498260498, "genuineness": 4.011539936065674, "identity": 0.3679503798484802, "hypothesis": "The door is still open. I'd put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/80647ec14798796bff773cb32a0e21d0c8078adf328bc179262446ccef89f8fe.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "37d5b82b95d12a0c2ff473fff1c19af49c48d29554ca219c549d6d375699cb6a", "generation_seconds_batch": 15.145513245020993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.632759928703308, "target_z": -1.2109374372653057, "ce": 6.260893821716309, "genuineness": 4.381826400756836, "identity": 0.5131244659423828, "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/vn_VOLT_reg_high/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.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": "8110b3faa86a61b47d8729bc94f906232309d04e9f57cf0940c8415934c1184e", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4909a67fb15d852876718922433cc7ce3e985ec0561cc619e8a76c428785efe", "generation_seconds_batch": 16.91149204794783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7090017795562744, "target_z": 0.028320375569815474, "ce": 6.213237762451172, "genuineness": 4.369274139404297, "identity": 0.47582289576530457, "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/vn_VOLT_reg_high/8110b3faa86a61b47d8729bc94f906232309d04e9f57cf0940c8415934c1184e.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "81809debc96eb7bbd4123d7b1eac505f43f9d273b3eb32b33f66dcd543e35bae", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "13cd382281d9e33ff9b2c955ccc697e4550703ec5845cd12887e6fb76334d434", "generation_seconds_batch": 15.871326908003539, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5581269264221191, "target_z": -1.296874934584336, "ce": 6.078212261199951, "genuineness": 4.444586753845215, "identity": 0.6168951392173767, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/81809debc96eb7bbd4123d7b1eac505f43f9d273b3eb32b33f66dcd543e35bae.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "818aacacda920a638e01fbad4d18684b30a7b953a27733ac01f3c85d5011a944", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "aafdb1595f6539d5a821be9eed6d35dc32e87fbb42017a64167154e8df056171", "generation_seconds_batch": 15.498747089062817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7687928676605225, "target_z": 0.09716788694690777, "ce": 6.09409761428833, "genuineness": 3.7542223930358887, "identity": 0.6192218661308289, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/818aacacda920a638e01fbad4d18684b30a7b953a27733ac01f3c85d5011a944.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": "818bf9a77c0098ab93e9dd8d08f486f82df1f5df7f60f822c00374ab33e52790", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "433491f23ed6f4371e315225e568664d29294eb47caad5618ab2532897a26941", "generation_seconds_batch": 14.997609446989372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.591963529586792, "target_z": -0.10644539808996213, "ce": 5.919358730316162, "genuineness": 4.049196243286133, "identity": 0.4986553192138672, "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/vn_VOLT_reg_high/818bf9a77c0098ab93e9dd8d08f486f82df1f5df7f60f822c00374ab33e52790.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "8203da7c2c0d3f9cc853afaf8db67967720afc5bd6ecc3b51a8a5df4e2c407f7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "33af7274fb8d8b30ba707731b3169f2acb2ade13ca2c5d52928cccff7e78ade6", "generation_seconds_batch": 16.621975144022144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5537989139556885, "target_z": -0.15039072325754463, "ce": 6.09409761428833, "genuineness": 3.8420867919921875, "identity": 0.656089186668396, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8203da7c2c0d3f9cc853afaf8db67967720afc5bd6ecc3b51a8a5df4e2c407f7.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "820f2865cde44cae870181f4cb62beb4f1ad11276f81d04bcf13ab81782e5a19", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0330b979ed251b5e65eee53c050b15940b20ceb4d9e41f68d7c63657113965cb", "generation_seconds_batch": 16.201087119989097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6056206226348877, "target_z": -1.2421874737264955, "ce": 6.205295085906982, "genuineness": 4.425758361816406, "identity": 0.5088586807250977, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/820f2865cde44cae870181f4cb62beb4f1ad11276f81d04bcf13ab81782e5a19.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "828a34c05351fbf96471c83883fb3dbd1d069579aa8d6329272d59f62bf1854e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "53ef12e7c80b2b4fb020bf7fd51cc41e95ccfc5bcc509026f812db6561ff6e67", "generation_seconds_batch": 21.078369597904384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1416213512420654, "target_z": -0.6249999056298616, "ce": 5.689021587371826, "genuineness": 3.9173994064331055, "identity": 0.5065457820892334, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/828a34c05351fbf96471c83883fb3dbd1d069579aa8d6329272d59f62bf1854e.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "82f10c290fe0e63cd53af30c1d601d2b92d1cb42e69d92de8db480b2ac2f6874", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9e949b7cd0460e85f43e274b2d65080c32340ab6de9a000417c6797d77dcf964", "generation_seconds_batch": 19.35256314696744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3138734102249146, "target_z": -1.5781249882037327, "ce": 6.24500846862793, "genuineness": 4.080576419830322, "identity": 0.23945412039756775, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/82f10c290fe0e63cd53af30c1d601d2b92d1cb42e69d92de8db480b2ac2f6874.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "830247a30827bc8a5de05c8e3dda37c961e1166bcf92564204f1830df514893c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8b8dcc3988333dccd13b357414606a9c6fc8fadf3bab803ce576ec1c1c6cee84", "generation_seconds_batch": 14.803139630006626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8295196294784546, "target_z": -0.9843749817694051, "ce": 6.260893821716309, "genuineness": 4.093128204345703, "identity": 0.39051198959350586, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/830247a30827bc8a5de05c8e3dda37c961e1166bcf92564204f1830df514893c.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "8365b12e196c8aa918c07910a768b02de3a43e9db270a44f6f709e5ffc47768c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "de0b810c560e1cee545904a436dfdcca3eda9694262dfcf19204831474ce30c0", "generation_seconds_batch": 21.785729334922507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7141776084899902, "target_z": -1.1171876024130478, "ce": 6.324435234069824, "genuineness": 4.042920112609863, "identity": 0.6039730310440063, "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/vn_VOLT_reg_high/8365b12e196c8aa918c07910a768b02de3a43e9db270a44f6f709e5ffc47768c.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "839b96c12394eac29c454c95841166031959f70e404fb6bec90c8741045a911d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a140e589708b6b9ccbe74babe6312f428669d02ec1c2dba46b59be689b9aa5b8", "generation_seconds_batch": 21.553226838004775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3638241291046143, "target_z": -0.369140566688906, "ce": 6.205295085906982, "genuineness": 4.375550270080566, "identity": 0.6423763036727905, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/839b96c12394eac29c454c95841166031959f70e404fb6bec90c8741045a911d.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "839b98844a0f4dbbcea1b3d3bfa95593ba3918f5f07874721257cf68aba20a9f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "44d5800ae57ed444e1e9a806979625cba57ba48c93c5bcf80896a26a52741b9d", "generation_seconds_batch": 21.394090145011432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8702285289764404, "target_z": -0.9374999957104483, "ce": 5.982900142669678, "genuineness": 4.074300289154053, "identity": 0.44670575857162476, "hypothesis": "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/vn_VOLT_reg_high/839b98844a0f4dbbcea1b3d3bfa95593ba3918f5f07874721257cf68aba20a9f.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": "84c05506a1120fe60379aee338cdd2735cf9c87f2be2ad281b39299ab5f99eac", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f8c587bcf2b26338245bd644071c3701cf1d4ebc5f20f4a8b321ffbefce88b6", "generation_seconds_batch": 21.277879680041224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9007601737976074, "target_z": -0.9023437904826446, "ce": 5.982900142669678, "genuineness": 3.9550557136535645, "identity": 0.637602686882019, "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/vn_VOLT_reg_high/84c05506a1120fe60379aee338cdd2735cf9c87f2be2ad281b39299ab5f99eac.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "84d142b18d5bd870fac713260655292284d83fffd12fcd6f398186ac00cdbabf", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c41acb919d03c23c699434463bc8c0e310c87a53ad9603e7fbcb6a5a67c6008a", "generation_seconds_batch": 21.289375439984724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3561038970947266, "target_z": 0.7734376131369273, "ce": 6.022613525390625, "genuineness": 3.8671910762786865, "identity": 0.4754653871059418, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/84d142b18d5bd870fac713260655292284d83fffd12fcd6f398186ac00cdbabf.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "84f49fd6296eb7892f0edcea50cdcd54a8690904ded51f96996c3b50ca52b383", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "44af10bbca3ac8c19d193065c8dbaaecfc8da18f66e06ff73600396a58cde24e", "generation_seconds_batch": 20.397494712960906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4563546180725098, "target_z": -1.414062468364556, "ce": 6.133810997009277, "genuineness": 4.074300289154053, "identity": 0.7210224866867065, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/84f49fd6296eb7892f0edcea50cdcd54a8690904ded51f96996c3b50ca52b383.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "850f527405f7c5bd004cf2c20877dffb6249724de6a291f2bafdb7f31eea8553", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5344d529387cc101a6824875ce2370d142ca571ea914cff82efe319729a4b46c", "generation_seconds_batch": 20.350313398987055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7820258140563965, "target_z": -1.0390625798929012, "ce": 6.316492557525635, "genuineness": 4.469690799713135, "identity": 0.44490525126457214, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/850f527405f7c5bd004cf2c20877dffb6249724de6a291f2bafdb7f31eea8553.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "854455414eb7e0bd9ae444a7dd60f14e75f5a815d67c5044785c7c21e231fa1a", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "23e986fa066d64610f8b65b9170e89aa3a386e3ff0ce518700992435a2e6f7c3", "generation_seconds_batch": 16.21279080293607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.490278720855713, "target_z": -1.3749999571044826, "ce": 6.117925643920898, "genuineness": 4.168440818786621, "identity": 0.5267305970191956, "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/vn_VOLT_reg_high/854455414eb7e0bd9ae444a7dd60f14e75f5a815d67c5044785c7c21e231fa1a.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "857983508885b6d21b5d1ed770763c0c2cf5f0913456810827d511a5645f83a3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "87e35ef7e8e1cb0db96cdfc2a025ae3ad060f70d60cfa8e3061febc2644e024e", "generation_seconds_batch": 20.640695137903094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.951646327972412, "target_z": -0.8437500235925346, "ce": 5.982900142669678, "genuineness": 3.8671910762786865, "identity": 0.496215283870697, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/857983508885b6d21b5d1ed770763c0c2cf5f0913456810827d511a5645f83a3.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "858e465e0302f5f00627122b4934a042f9a91bf7677f9a7837461e5344997738", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "69d2914fdee65a5a29c5026da86fcb306f74284d2e5c9087786cd44040e1e57f", "generation_seconds_batch": 22.144355228054337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4224305152893066, "target_z": -1.4531249796246293, "ce": 5.677107334136963, "genuineness": 3.7040140628814697, "identity": 0.4121602773666382, "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/vn_VOLT_reg_high/858e465e0302f5f00627122b4934a042f9a91bf7677f9a7837461e5344997738.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "85fa1c7cd7f7aeb9efc2bf8a4f426420c0227d02ec042a6ada96841a36a61a64", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf1f6bd3c9f988afe2ecca7c8e372cf51c0336d5f8fa837a6f24fdcba96e4de4", "generation_seconds_batch": 18.57311585196294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9591917991638184, "target_z": 0.3164061215815447, "ce": 5.982900142669678, "genuineness": 3.562803030014038, "identity": 0.6210505962371826, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/85fa1c7cd7f7aeb9efc2bf8a4f426420c0227d02ec042a6ada96841a36a61a64.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "86523a97665c3242ae5c0f71c2fdcdba1bb9abe3fde3334526db7c8ea09a3d2d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4ca7cc96dbd48828b4cbd0dac8adacc29f7a237d1bf5c76d40d4fd0810e155b1", "generation_seconds_batch": 22.212902792030945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4970635175704956, "target_z": -1.3671874823055992, "ce": 6.221180438995361, "genuineness": 4.375550270080566, "identity": 0.6099530458450317, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/86523a97665c3242ae5c0f71c2fdcdba1bb9abe3fde3334526db7c8ea09a3d2d.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "86bb4540989084699f29bbbd4b2a9b4c24a3b655bbac102193f828a59e2d3ba3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b05a492d6a1c6686bc52f27dc817bf7ba36bfc8c00f376552a0be06053c1e620", "generation_seconds_batch": 22.403783822082914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2867341041564941, "target_z": -1.6093750246649225, "ce": 6.141753673553467, "genuineness": 4.080576419830322, "identity": 0.40780729055404663, "hypothesis": "La porte 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/vn_VOLT_reg_high/86bb4540989084699f29bbbd4b2a9b4c24a3b655bbac102193f828a59e2d3ba3.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "86c91c216845e9d6a65ec78a5a53d7fcab15940806b2bf23fe632f65d147dc28", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3f5903154fb99cee015a2c4aeefa9095b432a0f123830df7b38eb9fc4fe186b1", "generation_seconds_batch": 21.495117209968157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.567368745803833, "target_z": -0.13476549912846603, "ce": 5.871703147888184, "genuineness": 4.017816066741943, "identity": 0.6768905520439148, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/86c91c216845e9d6a65ec78a5a53d7fcab15940806b2bf23fe632f65d147dc28.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "86de1cbd4b8641822c544fd10401e9ea39f579ce32ab94f9958a38facf1d43c8", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a0faa530250987c5c002a74f10183ec1f637daf30394a84d748d97e7a3884a16", "generation_seconds_batch": 21.323709243093617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8675968647003174, "target_z": 0.21093750589813365, "ce": 5.700935363769531, "genuineness": 4.162164688110352, "identity": 0.5301694273948669, "hypothesis": "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/vn_VOLT_reg_high/86de1cbd4b8641822c544fd10401e9ea39f579ce32ab94f9958a38facf1d43c8.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "86ee0c39e08308afd81135b480503a3d5bc72b91ff82b73cd410ad3cf92e0623", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d91408c3e26d4f598d4a7ca9145736befa6b67e6950cb2f14829fc0e2ef0b8b7", "generation_seconds_batch": 21.536784865078516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2595947980880737, "target_z": -1.6406250611261124, "ce": 6.221180438995361, "genuineness": 4.256305694580078, "identity": 0.6865699887275696, "hypothesis": "La porte 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/vn_VOLT_reg_high/86ee0c39e08308afd81135b480503a3d5bc72b91ff82b73cd410ad3cf92e0623.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "8769052c50b89e12d0a8052ffa9b7eadbb7671b3873dc6d36478ad67f13bf2a4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b7ac7126c059c295e0c0fac2f3a8d1201290d23403ce23b531851faa33bf152f", "generation_seconds_batch": 15.23469007993117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.860811948776245, "target_z": 0.20312489383359436, "ce": 5.911416053771973, "genuineness": 3.8671910762786865, "identity": 0.3520197868347168, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8769052c50b89e12d0a8052ffa9b7eadbb7671b3873dc6d36478ad67f13bf2a4.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "876980beb4444b9bf475528a7d087681d4ae2aa1bb7212063021b07d1dd77868", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3e128370fb7653ffecbaf29ad76619d5d4d6c5d9f303b56147d41a6ea081fcae", "generation_seconds_batch": 20.614354143035598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8532664775848389, "target_z": -0.957031251340485, "ce": 6.332377910614014, "genuineness": 4.2249250411987305, "identity": 0.6181399822235107, "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/vn_VOLT_reg_high/876980beb4444b9bf475528a7d087681d4ae2aa1bb7212063021b07d1dd77868.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "87e6b86f99cf23aa5f775af4c62a6ccd11e2e1aa994bb896f7b8bb6c42bacc52", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc3bd877f7cba765d180509de4f34725b8ce03684a6482fc3a69548f03584ad3", "generation_seconds_batch": 20.74223771796096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.134836435317993, "target_z": -0.6328125176944009, "ce": 5.871703147888184, "genuineness": 4.243753433227539, "identity": 0.5422296524047852, "hypothesis": "La porte 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/vn_VOLT_reg_high/87e6b86f99cf23aa5f775af4c62a6ccd11e2e1aa994bb896f7b8bb6c42bacc52.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": "8805680a9e3a5885b6ba1b189af55366dfc030ca2d5dbcde72131764d0feb138", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "923153a7a7286cc73150447b0ffb7f87ee1541914f0bcc9c0b716d570e6d30b8", "generation_seconds_batch": 13.673604854033329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7955955266952515, "target_z": -1.0234374930294785, "ce": 6.213237762451172, "genuineness": 4.174716949462891, "identity": 0.7734776735305786, "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/vn_VOLT_reg_high/8805680a9e3a5885b6ba1b189af55366dfc030ca2d5dbcde72131764d0feb138.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "8829c7018edd031b5b67eeeadeeb514ac12e9b9ce00baf72a97d5bd59acad364", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "02bf1659ea6f7e722eaaead1fb2439de9163838baff8988f593c86dba6db1521", "generation_seconds_batch": 14.475291953072883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5232672691345215, "target_z": -0.1855469284853483, "ce": 6.022613525390625, "genuineness": 4.055472373962402, "identity": 0.548737645149231, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8829c7018edd031b5b67eeeadeeb514ac12e9b9ce00baf72a97d5bd59acad364.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "88507961b2768a4af170b211b2d52b007ec290df54d4234e2a450269f6ac7c0c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c6cccb3fa4816c55940f36c15804f64e664cf88a7330a51c580b9135c912fc79", "generation_seconds_batch": 16.631165848928504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.734532117843628, "target_z": -1.0937500407507417, "ce": 6.062326908111572, "genuineness": 4.055472373962402, "identity": 0.7207117080688477, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/88507961b2768a4af170b211b2d52b007ec290df54d4234e2a450269f6ac7c0c.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "8874e33952fcb53a0f4d23a5243ee3751dc0f7f55067b766242c7ea588e2eea9", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a69339aadee40978783cfafec75d9a0f1ad01c6e798a5df0c6cde3411820abad", "generation_seconds_batch": 20.551902545965277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479166030883789, "target_z": -0.236328083310919, "ce": 6.046441555023193, "genuineness": 3.898571252822876, "identity": 0.7369544506072998, "hypothesis": "De deur 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/vn_VOLT_reg_high/8874e33952fcb53a0f4d23a5243ee3751dc0f7f55067b766242c7ea588e2eea9.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "89ac99ccf5f1720a75a1fb4eb0af3408c8a637b0312770675da07ec5fbc82f01", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "82f490c07047d829bb89e90348f572d7454e930158bf8740cc9604ed7e586dd4", "generation_seconds_batch": 21.622066995943896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.988027334213257, "target_z": 0.34960931105886933, "ce": 5.855817794799805, "genuineness": 3.6663577556610107, "identity": 0.45076626539230347, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/89ac99ccf5f1720a75a1fb4eb0af3408c8a637b0312770675da07ec5fbc82f01.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "8a42d1ac8c7292b9350e2ec32db1f2b8da858c8ed846ab0d12ecefbb22346136", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "30c419c2a5584f8e5b052195ccbe40354c054a520ad516817852439ba9fe5290", "generation_seconds_batch": 21.239045281079598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3206582069396973, "target_z": -1.5703125134048492, "ce": 6.459460258483887, "genuineness": 4.457139015197754, "identity": 0.5439568758010864, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8a42d1ac8c7292b9350e2ec32db1f2b8da858c8ed846ab0d12ecefbb22346136.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "8a9f385edb88e73acd681cf72795c8c49cec67ff42fbd1d0f4388947b67aadd6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8282774b7ce3acadd3c5f88392b9b85daafbea546287ae22be3a7e3077b34d0f", "generation_seconds_batch": 15.269713629968464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5513420104980469, "target_z": -1.3046875466488752, "ce": 6.141753673553467, "genuineness": 3.9927117824554443, "identity": 0.5983664989471436, "hypothesis": "La porte 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/vn_VOLT_reg_high/8a9f385edb88e73acd681cf72795c8c49cec67ff42fbd1d0f4388947b67aadd6.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "8ac012dc82b9a439b613e72f9b1e8bcede3edd7ab457e0b626457a7d35f54c5f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d0b33f609451722cdf56fdc40fc5d56599641bab10b12b92028ef6fb3ec50b77", "generation_seconds_batch": 20.74223771796096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.982177972793579, "target_z": -0.8085938183647309, "ce": 5.974957466125488, "genuineness": 4.293961524963379, "identity": 0.5548511743545532, "hypothesis": "La porte 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/vn_VOLT_reg_high/8ac012dc82b9a439b613e72f9b1e8bcede3edd7ab457e0b626457a7d35f54c5f.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": "8af1abe6bc4ad4d96e05728f847f557d8edeb1f1ee5bc6761dcc402dbcfec243", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "25f00a7005c5b1ebe918ee24b2b063241c9b0e28c4ab6d3e00f06bdb6ba9a50d", "generation_seconds_batch": 15.047432180959731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8702285289764404, "target_z": -0.9374999957104483, "ce": 6.1020402908325195, "genuineness": 4.218649387359619, "identity": 0.6117210984230042, "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/vn_VOLT_reg_high/8af1abe6bc4ad4d96e05728f847f557d8edeb1f1ee5bc6761dcc402dbcfec243.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "8b3d0af79d67ba12a55fb6dc9951ea86b168bd015b3ac3fbb238961ca3bae49f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "8a17f60f0b0d4a12c5c770834ae2854f02c80b9851d1590b2eabf9a408d47943", "generation_seconds_batch": 21.785729334922507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3817216157913208, "target_z": -1.499999965683586, "ce": 6.300607204437256, "genuineness": 3.9425034523010254, "identity": 0.2611362040042877, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hin.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8b3d0af79d67ba12a55fb6dc9951ea86b168bd015b3ac3fbb238961ca3bae49f.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": "8b919a5838c20e15dd5d4cbc050ad69175fda90e13d318dd265ae006d88027b2", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e782b0f4aee6a78d06b615b1a0e2d35a6e4dff386cfa582b6d3bc80447e90949", "generation_seconds_batch": 15.022433908074163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9245071411132812, "target_z": -0.8749999227880686, "ce": 6.165581703186035, "genuineness": 4.049196243286133, "identity": 0.4981151521205902, "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/vn_VOLT_reg_high/8b919a5838c20e15dd5d4cbc050ad69175fda90e13d318dd265ae006d88027b2.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "8bae7a649ca167c502b38fc06c9ffb378dd58507f2bdac6c6fcbdd4fbe4dbe2c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "194d0b3f314683fd89e51fc9c4293342b65179ccfa381884503d0df06d337d67", "generation_seconds_batch": 16.201087119989097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6395447254180908, "target_z": -1.2031249624664222, "ce": 6.062326908111572, "genuineness": 4.507347106933594, "identity": 0.5916078686714172, "hypothesis": "He encontrado la cajita. Esta junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8bae7a649ca167c502b38fc06c9ffb378dd58507f2bdac6c6fcbdd4fbe4dbe2c.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "8bbb31cd2c049ecd79b3b517cc9c1e725f3307646509c5b94aa685cc828bfb29", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b70b39906d8c68399191eeaddd28b6f18238b4cc748d5c5b6f51f8abf7f49306", "generation_seconds_batch": 19.35256314696744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.476709008216858, "target_z": -1.3906250439679053, "ce": 6.2767791748046875, "genuineness": 3.9299514293670654, "identity": 0.4859943985939026, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8bbb31cd2c049ecd79b3b517cc9c1e725f3307646509c5b94aa685cc828bfb29.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "8c11017325ce23618458c94d5b362ef1398141469557db4e18eba7141b38d352", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e58e8db61912a2220a6d01b6465815e273564517898843e1491cc4eed77414ea", "generation_seconds_batch": 21.77492333203554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8227348327636719, "target_z": -0.9921874565682886, "ce": 6.165581703186035, "genuineness": 4.256305694580078, "identity": 0.7139296531677246, "hypothesis": "La porte 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/vn_VOLT_reg_high/8c11017325ce23618458c94d5b362ef1398141469557db4e18eba7141b38d352.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": "8c48b19844fb9e84d3693e179f8c05cd27dc785a34a6a7135b19c41ba09ca9c2", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Escribí el número en el sobre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d8e447e2ba950ef2408719bc9b0fb980ebc93fa9fbf605c52dbf4a2baa1c953", "generation_seconds_batch": 13.616705731023103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9584312438964844, "target_z": -0.8359374115279953, "ce": 6.086154937744141, "genuineness": 4.055472373962402, "identity": 0.7003811597824097, "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/vn_VOLT_reg_high/8c48b19844fb9e84d3693e179f8c05cd27dc785a34a6a7135b19c41ba09ca9c2.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "8c777aee0829d5f06fe8ee3810452749aa79a296ec85add197eb0f29284b881a", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b1a397223b9e27db2a303aef4f76cb9217f7dd161471f44a0f08f49be314596a", "generation_seconds_batch": 14.89258951798547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0262794494628906, "target_z": -0.7578123890078486, "ce": 6.078212261199951, "genuineness": 4.356721878051758, "identity": 0.47726142406463623, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8c777aee0829d5f06fe8ee3810452749aa79a296ec85add197eb0f29284b881a.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "8c8ca90ae31c80839d376a9dd3c8ba73255d4b1fbb7d7265aa8ec88511dfa35f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5c6d2dc6aa288b78f03215c6ab32b61afa2b24a385f4d4a7074c9eabd4f27e4c", "generation_seconds_batch": 21.504841862013564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4510912895202637, "target_z": 0.8828125348526079, "ce": 5.252174377441406, "genuineness": 3.9550557136535645, "identity": 0.6035402417182922, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8c8ca90ae31c80839d376a9dd3c8ba73255d4b1fbb7d7265aa8ec88511dfa35f.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": "8ca904560ecb2e18f2676b3af3a210d2815b6fa0b0070e5b64b782e749dec328", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "833010d8813a9fc65f963dcac0e60f0b114cfc6a707a936793daa3ac69f534e4", "generation_seconds_batch": 13.596925228950568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5877230167388916, "target_z": -0.1113282119974713, "ce": 6.1020402908325195, "genuineness": 4.413206577301025, "identity": 0.6977983713150024, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.13636363636363635, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8ca904560ecb2e18f2676b3af3a210d2815b6fa0b0070e5b64b782e749dec328.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "8d28c313a140cb09f44f1fd71890a51da4a553e2c1a7756f5946cc3297d1ff43", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cdadda61c4de984b063a32fb70aae47fa5994c2a1a53c14d6bd4ed5306b71340", "generation_seconds_batch": 15.648692439077422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.707392930984497, "target_z": -1.1249999399462756, "ce": 6.181467056274414, "genuineness": 4.137060642242432, "identity": 0.7717984914779663, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8d28c313a140cb09f44f1fd71890a51da4a553e2c1a7756f5946cc3297d1ff43.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "8d30793bc912cc47b2b913c45a56c905c82299f4d201b7f1d75921ddd63470af", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e3efe6693b9420c86cb0cdba4ec9f00eaaa26b4c55bc8dc7385944f5228acbf3", "generation_seconds_batch": 21.448631189996377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2731645107269287, "target_z": -1.6249999742626895, "ce": 6.403861999511719, "genuineness": 4.162164688110352, "identity": 0.5479272603988647, "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/vn_VOLT_reg_high/8d30793bc912cc47b2b913c45a56c905c82299f4d201b7f1d75921ddd63470af.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "8d988857c0ae6a3ec000b60e31445a9848321ce33be281e7b1abf3116c71be0a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d48f98cdf6430f4eecd7e463d0ceb8e2ea5c78d83279e341278c7cfaa4c059e1", "generation_seconds_batch": 21.205840138019994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.013470411300659, "target_z": 0.3789061945039243, "ce": 5.935244083404541, "genuineness": 3.6287014484405518, "identity": 0.5660718679428101, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8d988857c0ae6a3ec000b60e31445a9848321ce33be281e7b1abf3116c71be0a.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "8df9fbddea204932b7cf2dc6fb5937a2add72cff5f590454c6faa3e483f6c961", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6fe05e7fbf534b27d5e03a49726638ed310678dd97a3018986e196a1bed3c90c", "generation_seconds_batch": 21.828391343005933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8353688716888428, "target_z": 0.17382801038853937, "ce": 6.197352409362793, "genuineness": 3.7793264389038086, "identity": 0.6845729351043701, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8df9fbddea204932b7cf2dc6fb5937a2add72cff5f590454c6faa3e483f6c961.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "8e008102d3f3e15987a3c51bfadc6b7f63f0f7dbd5d87850679a5b13d507a495", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "aef0d17ee296731b55b7e63fe2b77f0b19f6e5f02c21cd686d48012a04109b08", "generation_seconds_batch": 20.72035631502513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.659899115562439, "target_z": -1.1796875380697718, "ce": 6.372091293334961, "genuineness": 4.13078498840332, "identity": 0.3999568223953247, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8e008102d3f3e15987a3c51bfadc6b7f63f0f7dbd5d87850679a5b13d507a495.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "8e38e3de2c3bdd6082cdd39b5ff97e904bcc10376c406007ab3d1f537f3af04e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f727dfc73127297aa95a73e77beed8537c35a5523311c7b5fa7622360542fc8c", "generation_seconds_batch": 21.539494332973845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3740012645721436, "target_z": -0.35742192312340865, "ce": 5.879645347595215, "genuineness": 4.18099308013916, "identity": 0.6433340311050415, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8e38e3de2c3bdd6082cdd39b5ff97e904bcc10376c406007ab3d1f537f3af04e.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": "8e5d71ba23cacdba70428a183fdc2a98cd5bc56aa57c7a935c9aa15835d5ee16", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bbc320a73e3004c08b7705b3fbdf9da7fca68113f59bdc81d5def01689051b8e", "generation_seconds_batch": 14.788210667087696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6394572257995605, "target_z": -0.051757937232121784, "ce": 6.109982967376709, "genuineness": 4.105680465698242, "identity": 0.3764491379261017, "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/vn_VOLT_reg_high/8e5d71ba23cacdba70428a183fdc2a98cd5bc56aa57c7a935c9aa15835d5ee16.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "8e970ea400dac5f1641c8399169f39f794b2282dc3c2d25d499970495e68321b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "406be9e0429d4d62cc0f0850443043896ddcd6c3b7f35151c76a7830b57355e4", "generation_seconds_batch": 20.113678629044443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9584312438964844, "target_z": -0.8359374115279953, "ce": 5.903473377227783, "genuineness": 4.143336772918701, "identity": 0.4744405746459961, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8e970ea400dac5f1641c8399169f39f794b2282dc3c2d25d499970495e68321b.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "8ecb26ac520a4cf51619ddaffa25191e02b74d8530049e280b1eb52bdf356e54", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "66d53b099c6d66d24830097cba8b1a4b31c013aea67eea57b9a39a4d8b51e204", "generation_seconds_batch": 15.802890754071996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5784813165664673, "target_z": -1.2734375101876854, "ce": 6.125868320465088, "genuineness": 4.2374773025512695, "identity": 0.42526811361312866, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8ecb26ac520a4cf51619ddaffa25191e02b74d8530049e280b1eb52bdf356e54.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "8ed81378303ac032bc30e2bdbbb2a99d7ea589e08a112b5005c0e11958f16899", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "80177d0b4837e6c744591cbf37f54af70bc4994456200f9ba8c660df74c4be2d", "generation_seconds_batch": 21.176148075028323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4171671867370605, "target_z": 0.8437500235925346, "ce": 5.6413655281066895, "genuineness": 3.9425034523010254, "identity": 0.8009964823722839, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8ed81378303ac032bc30e2bdbbb2a99d7ea589e08a112b5005c0e11958f16899.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "8ee6f60921008472b465dcf7535e5e8b6d0c844e64b6cc437e4e7abbd00ca387", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6e8741e41237945e13cf6a1ea8718a56fdea0f15f41f55b110cf59baa62b2c04", "generation_seconds_batch": 22.475107604055665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.039849042892456, "target_z": -0.7421874394100816, "ce": 5.411027908325195, "genuineness": 3.71028995513916, "identity": 0.6038590669631958, "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/vn_VOLT_reg_high/8ee6f60921008472b465dcf7535e5e8b6d0c844e64b6cc437e4e7abbd00ca387.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "8eefbd20710872d145eeb92f11a24cf3eca13c2471bb37b9e7747fdb5d14230c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a32bfc926453840e7431336b777bb2389e71d198e0945aadd6c07dc105165862", "generation_seconds_batch": 16.557443215046078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.436000108718872, "target_z": -1.437500030026862, "ce": 6.157639026641846, "genuineness": 4.18099308013916, "identity": 0.3759191334247589, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8eefbd20710872d145eeb92f11a24cf3eca13c2471bb37b9e7747fdb5d14230c.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "8f46bd845d83f650ee5c254065be536bd2af5e35882926f2e1ed309f7319f0f6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "db67ca86c9d4b9cfa43ae4a7e91163af10c8a4f4ba002dacfa18768f5a2ada47", "generation_seconds_batch": 15.861268915003166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.419747352600098, "genuineness": 4.337893962860107, "identity": 0.5210009813308716, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/8f46bd845d83f650ee5c254065be536bd2af5e35882926f2e1ed309f7319f0f6.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "907628e31fa0aae4e984e298b8726c4353e8374c773730ec8988df681c9f4b81", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0832e3db3da407d333a7ae0da8b82353561319dde4eb1d5d07b44f98b8b3309b", "generation_seconds_batch": 15.490249214926735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0568110942840576, "target_z": -0.7226561837800449, "ce": 6.109982967376709, "genuineness": 4.168440818786621, "identity": 0.4310513734817505, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/907628e31fa0aae4e984e298b8726c4353e8374c773730ec8988df681c9f4b81.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "90f17a7a885d6befcb8acef675d8a06609da23a3eaa118ec30fcb1bfcf5c22ce", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5c8b54b707b43b329f1c59d9c190ed279fb87a2043abd75a3f35e855629aa7f6", "generation_seconds_batch": 14.896244908100925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2935189008712769, "target_z": -1.601562549866039, "ce": 6.149696350097656, "genuineness": 4.469690799713135, "identity": 0.6585575938224792, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/90f17a7a885d6befcb8acef675d8a06609da23a3eaa118ec30fcb1bfcf5c22ce.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "912215ddab5e0c41ca01a71179869991934b29aaaaf2db723d3a5c8ea312e7cc", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4918c5ebd689f1feab7351f145b61d2490498c3955e4bdad8db8c87c950fb762", "generation_seconds_batch": 15.404041143017821, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7827866077423096, "target_z": 0.11328122774795034, "ce": 6.046441555023193, "genuineness": 3.672633647918701, "identity": 0.42090171575546265, "hypothesis": "Ik 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/vn_VOLT_reg_high/912215ddab5e0c41ca01a71179869991934b29aaaaf2db723d3a5c8ea312e7cc.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "9155a336caa4d37df85e2166678700086ed648207b6a522f7de352d7742ec2e9", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "62dc5157ce52da0a8c94c6ff7bfd936d774b38801cb5a7a244930da4d17bf155", "generation_seconds_batch": 15.517187390010804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2595947980880737, "target_z": -1.6406250611261124, "ce": 6.38797664642334, "genuineness": 4.18099308013916, "identity": 0.5494123697280884, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9155a336caa4d37df85e2166678700086ed648207b6a522f7de352d7742ec2e9.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "916d78e45acbfb087f39b584cc9c0c5de4f17a357ce0bd55250a4bba84d85d6c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "13d73878a9048340741dff0c69037790949c5b1fdf20e70203ecc9d40d64423a", "generation_seconds_batch": 20.869164578965865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0161020755767822, "target_z": -0.7695313071046576, "ce": 6.165581703186035, "genuineness": 4.030367851257324, "identity": 0.37932974100112915, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/916d78e45acbfb087f39b584cc9c0c5de4f17a357ce0bd55250a4bba84d85d6c.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "918375a009ebb92781ba6726634dc57fe5c758d0c8ad843ca848f18720cabe8b", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce9de1b9d023b5ab4da71d03291e4d3ab4eac62dc8c7e7199e8aa95bc4aab80f", "generation_seconds_batch": 15.214859004947357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.476709008216858, "target_z": -1.3906250439679053, "ce": 6.1894097328186035, "genuineness": 4.3881025314331055, "identity": 0.5540507435798645, "hypothesis": "La porte 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/vn_VOLT_reg_high/918375a009ebb92781ba6726634dc57fe5c758d0c8ad843ca848f18720cabe8b.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "92e7644cb37f3dc214762d0e2c4fde137260261a0fce3e7063efb7a12e9ff015", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "eeb432a23dfb5c28ac8a3c35f1684a35188d96e11801a26050b6f93999a46f88", "generation_seconds_batch": 20.171180142904632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9652159214019775, "target_z": -0.8281250739947675, "ce": 6.316492557525635, "genuineness": 4.306513786315918, "identity": 0.6117512583732605, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/92e7644cb37f3dc214762d0e2c4fde137260261a0fce3e7063efb7a12e9ff015.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "94035da6c7c5fff5ae51456dbf81470b7482c84a807d108526d4139b8419c67d", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "67ef40fda2d70f04961d54c48dade3be90cefa8cad21d152c089c08f8c4ef571", "generation_seconds_batch": 16.16089773294516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0228869915008545, "target_z": -0.7617186950401182, "ce": 6.356205940246582, "genuineness": 4.444586753845215, "identity": 0.471330851316452, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/94035da6c7c5fff5ae51456dbf81470b7482c84a807d108526d4139b8419c67d.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "95d2fa6c588cddec797ac2d3abbc42407d6ce0d5d47d147f9e9aa27a9acf738c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f8b6bae96c1be2c39740ee4f25f7ec841c10c7ed91a76a833c256fd9e8343fa5", "generation_seconds_batch": 20.578395624062978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0602035522460938, "target_z": -0.7187498777477753, "ce": 6.284721851348877, "genuineness": 4.331617832183838, "identity": 0.5487330555915833, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/95d2fa6c588cddec797ac2d3abbc42407d6ce0d5d47d147f9e9aa27a9acf738c.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "96ae3263980340b2b128038507ec504082c841f8a913c4f1e5360b2993936002", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "472b3f724b3071c13080e5eb673d2cacfe2dbb21628ec585369ef859eff4d998", "generation_seconds_batch": 21.436250232043676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2935189008712769, "target_z": -1.601562549866039, "ce": 6.062326908111572, "genuineness": 3.9801597595214844, "identity": 0.29637837409973145, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/96ae3263980340b2b128038507ec504082c841f8a913c4f1e5360b2993936002.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": "96c71f9780c8fc489e6dfc77d479753b3614994825b25a510ad66425f467f72c", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Your message arrived after I had left.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "733dd8bfd0f2f92ab51805f1b216459c361e18c254fb798ec42ef02d54e02fb0", "generation_seconds_batch": 15.19572552794125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.304456949234009, "target_z": -0.4374999613940343, "ce": 6.356205940246582, "genuineness": 3.8922953605651855, "identity": 0.39542096853256226, "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/vn_VOLT_reg_high/96c71f9780c8fc489e6dfc77d479753b3614994825b25a510ad66425f467f72c.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "96c8f53dca473d72e9b3ca5ccb9c7abae0196ad62c05648f59e8973bc94b66dc", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3f4204d4821023f2ad8d70a8a93b3c63d0e57a481927737acc39fe511a300a00", "generation_seconds_batch": 20.91957434802316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3163304328918457, "target_z": -0.4238280275467463, "ce": 6.1020402908325195, "genuineness": 3.9801597595214844, "identity": 0.5408303737640381, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/96c8f53dca473d72e9b3ca5ccb9c7abae0196ad62c05648f59e8973bc94b66dc.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": "96e7c28b06ae81cbc74661b46f244320c8f9836312e3e4ad7a1241800657f366", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e821b59930b9456e913bb6b140f1156da133b300ba49a87b39ee44f0ec2f4713", "generation_seconds_batch": 13.699734495952725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.948253870010376, "target_z": -0.8476563296248042, "ce": 5.9431867599487305, "genuineness": 4.017816066741943, "identity": 0.683899462223053, "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/vn_VOLT_reg_high/96e7c28b06ae81cbc74661b46f244320c8f9836312e3e4ad7a1241800657f366.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": "9739a1f6caec4d4d6142ad419dca0bc60544e713218273777fa79e845610f5bd", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "6a85393209d77dbd6fef3c4f68c18dc38b77edad278d3c41fce3b42ad8ca503e", "generation_seconds_batch": 16.25374490604736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.161975860595703, "target_z": -0.6015623439675554, "ce": 6.38797664642334, "genuineness": 4.532451152801514, "identity": 0.4202326834201813, "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/vn_VOLT_reg_high/9739a1f6caec4d4d6142ad419dca0bc60544e713218273777fa79e845610f5bd.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "982115e2ab177155cc4dc705e5931518149d7008fb0c0ed1dd6844af9e96261d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d8b78dfc9599d59f87cd9409745f1fd108a7c2ad684e1a6181ede306b564b749", "generation_seconds_batch": 21.303853031946346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1755452156066895, "target_z": -0.5859376689010999, "ce": 6.221180438995361, "genuineness": 3.873466968536377, "identity": 0.6255415678024292, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/982115e2ab177155cc4dc705e5931518149d7008fb0c0ed1dd6844af9e96261d.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "986aa06c44f3ced00aa2e0f9dd0a4269b570b2799ed385f2a72f0c5c763d4780", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "83fa3c8e9f6e3ad4c77859583b9ed1e5f4e7c65aa8e816fc41d7f9cba17144c5", "generation_seconds_batch": 21.28678158496041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.762432098388672, "target_z": 0.08984366608564402, "ce": 5.847874641418457, "genuineness": 3.7040140628814697, "identity": 0.6138988733291626, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/986aa06c44f3ced00aa2e0f9dd0a4269b570b2799ed385f2a72f0c5c763d4780.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "98aac608db68d145bdbf15d28e535da968bb169243781d2da7b2eb5b9fdd39c4", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "72a41a6a56777aad4b3eae8ab8ca81e3432da013c4dcb2e94e0cf2fcb8232ad4", "generation_seconds_batch": 15.54425799404271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7955955266952515, "target_z": -1.0234374930294785, "ce": 6.157639026641846, "genuineness": 4.099404335021973, "identity": 0.5499191880226135, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/98aac608db68d145bdbf15d28e535da968bb169243781d2da7b2eb5b9fdd39c4.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "98b864477277f147f0faec1ed5eb0c5b0b4d68031c3a0ecbfe1882fa80a716a6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd396490ac9ffdb488941e9892bb79807cd2873448d79f455a61008d556e5f57", "generation_seconds_batch": 21.717028753017075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5317482948303223, "target_z": -0.17578130067032996, "ce": 5.736677646636963, "genuineness": 3.8797430992126465, "identity": 0.6396471261978149, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/98b864477277f147f0faec1ed5eb0c5b0b4d68031c3a0ecbfe1882fa80a716a6.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": "995331a2df76988fc418232d75e5e6a28520fa54f51ae206b3c30a2ee0b2f500", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b8d5015ed0781fea87f3565c5d988bc19010f275ec484c4e6544cd2d1c3778a6", "generation_seconds_batch": 21.11279060097877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0423059463500977, "target_z": 0.41210938398124897, "ce": 5.935244083404541, "genuineness": 4.080576419830322, "identity": 0.6358956694602966, "hypothesis": "Pulquin a déplacé la petite chasse 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/vn_VOLT_reg_high/995331a2df76988fc418232d75e5e6a28520fa54f51ae206b3c30a2ee0b2f500.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "9959c00b35411f56175752ceec7683e41a452e655c3c52974a6ee8a56a95a369", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9c7faf05293f5ccbc8a7bc1e36ce13f0894864cd6828ec0ded97cecdf61c8548", "generation_seconds_batch": 20.44068189896643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.379089832305908, "target_z": -0.3515626013406599, "ce": 5.486483573913574, "genuineness": 4.005263805389404, "identity": 0.5843825340270996, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lientando.", "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/vn_VOLT_reg_high/9959c00b35411f56175752ceec7683e41a452e655c3c52974a6ee8a56a95a369.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "9983e12d4a1181e079e84084d6c3d7c95ae2cbf447f7f86b73f41c2b49e6b2ab", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7b85a44a170bb85ac612d9073d8cf1df1026cda6b7bf9557114274e4a10245b", "generation_seconds_batch": 15.712374120019376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.598835825920105, "target_z": -1.249999948525379, "ce": 6.403861999511719, "genuineness": 4.080576419830322, "identity": 0.5842568874359131, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9983e12d4a1181e079e84084d6c3d7c95ae2cbf447f7f86b73f41c2b49e6b2ab.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "998e9ae2b9db97691d1afc86f5f1f28b3ca6ea28c32e10b0fcbaaab74e840a04", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ad05f32ed52ab75c817f515f7ca94e0d5d4cc5a39c2bd0ed86a53ae194018aa0", "generation_seconds_batch": 21.669427786022425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.191746711730957, "target_z": -1.7187499463806033, "ce": 6.23706579208374, "genuineness": 3.8044304847717285, "identity": 0.42176365852355957, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/998e9ae2b9db97691d1afc86f5f1f28b3ca6ea28c32e10b0fcbaaab74e840a04.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "d9cdca8a4a635c9d45c607f29730b15bc7de6fd840fcab734f314f51fb28b453", "generation_seconds_batch": 13.503507282934152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.975393295288086, "target_z": -0.8164061558979586, "ce": 6.475345611572266, "genuineness": 4.883909225463867, "identity": 0.5672872066497803, "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/vn_VOLT_reg_high/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "9a2ef125a15b1d61225f60ce950c0d980ee2aa146c54f138e87d687e2464e526", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "edf3d2a54a7d8a3c1359153f5729e27fba57134779a44ac14f1fcc419cff8221", "generation_seconds_batch": 14.860142746008933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.124659299850464, "target_z": -0.6445311612598983, "ce": 6.1894097328186035, "genuineness": 4.2249250411987305, "identity": 0.4021739661693573, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9a2ef125a15b1d61225f60ce950c0d980ee2aa146c54f138e87d687e2464e526.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "9a3b0ed6a13a3bf936ea32cc20c6cbff56fd9fb665b50c22d830487d51b4619f", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a0291e319e2205d420c7540881d69a02d4903f8f771b09815ba432ccc859a4dd", "generation_seconds_batch": 15.366104502929375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3342278003692627, "target_z": -1.5546875638070823, "ce": 6.0305562019348145, "genuineness": 4.030367851257324, "identity": 0.6023225784301758, "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/vn_VOLT_reg_high/9a3b0ed6a13a3bf936ea32cc20c6cbff56fd9fb665b50c22d830487d51b4619f.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "9a988a8d605110b7fa0cba4b5175a3a57506908f0ea1592b063262d431e25118", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "06abe7ed3d4232355bfc45426feff1dc22704aa1929286e48c0475fd77b2f235", "generation_seconds_batch": 15.840456769918092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.213237762451172, "genuineness": 4.482243061065674, "identity": 0.6692315340042114, "hypothesis": "La porte 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/vn_VOLT_reg_high/9a988a8d605110b7fa0cba4b5175a3a57506908f0ea1592b063262d431e25118.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "9aace54c870e936bb77cfe7aba810a0e07cabd5ef8d82994b904b3a59a1df64a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "56bcb0c3add5ffc4290546cac13fb66662f747b68d524476913d7f84b8e82c19", "generation_seconds_batch": 19.902222548960708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.185722589492798, "target_z": -0.574218750804291, "ce": 6.046441555023193, "genuineness": 4.281409740447998, "identity": 0.8504825234413147, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9aace54c870e936bb77cfe7aba810a0e07cabd5ef8d82994b904b3a59a1df64a.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": "9aba877fb4958289c6eae3b32b7e29cb2f2a9e12322b910aa18d23a6821401f6", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The road turns left behind the bridge.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "3a8fad95c7eceb7b33f81237b3c82cecc8b114fde70a49e5db30153523fe4eac", "generation_seconds_batch": 15.75652514200192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.887190580368042, "target_z": -0.9179687400804116, "ce": 6.41180419921875, "genuineness": 4.15588903427124, "identity": 0.2259693145751953, "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/vn_VOLT_reg_high/9aba877fb4958289c6eae3b32b7e29cb2f2a9e12322b910aa18d23a6821401f6.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": "9afa2ad63de3dabea357290704e7b762fcb2fbd76e34dbc0e76e41c367e7c162", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "44f4cacecef48f256eb373f1e3560e0bb3618cfc32fd68583c719e2f2f87af0d", "generation_seconds_batch": 20.212786489981227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4834065437316895, "target_z": -0.23144526940340984, "ce": 5.871703147888184, "genuineness": 4.030367851257324, "identity": 0.5923002362251282, "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/vn_VOLT_reg_high/9afa2ad63de3dabea357290704e7b762fcb2fbd76e34dbc0e76e41c367e7c162.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "9b6a680cc92c2cbc444ddae64cc0512bd1174d2cdc319137eacc7578187305af", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e2e92977e78089ce0ac458b61415e6e1fe90caae68de732b4e976fd4960edbfd", "generation_seconds_batch": 15.029807192040607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5445572137832642, "target_z": -1.3125000214477587, "ce": 6.205295085906982, "genuineness": 4.582659721374512, "identity": 0.6727094054222107, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9b6a680cc92c2cbc444ddae64cc0512bd1174d2cdc319137eacc7578187305af.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "728bea22c1cbd93659efa2fc1548ec8c9805bbfc1f77395bbdd5af36dc98c52d", "generation_seconds_batch": 15.723141894908622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.768456220626831, "target_z": -1.0546875294906681, "ce": 6.165581703186035, "genuineness": 4.344170093536377, "identity": 0.5788429975509644, "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/vn_VOLT_reg_high/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "9c6b88ada2b0f48aaa16ddbeca84934a30607624edbd8ab5775bcf986b89ed92", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cc5d550d82e9dcd5b587ec46e27309b236c3e41780feafa4c74c5189af9e87c7", "generation_seconds_batch": 20.426635609008372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8404576778411865, "target_z": 0.17968760670259962, "ce": 5.669164657592773, "genuineness": 3.613011360168457, "identity": 0.4941086173057556, "hypothesis": "De deur 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/vn_VOLT_reg_high/9c6b88ada2b0f48aaa16ddbeca84934a30607624edbd8ab5775bcf986b89ed92.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "410d1dd0883900b219c4980a972c584772e9cebf2543aa14075b83956e0651c8", "generation_seconds_batch": 15.827121507027186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9448615312576294, "target_z": -0.8515624983914181, "ce": 5.879645347595215, "genuineness": 4.425758361816406, "identity": 0.7113455533981323, "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/vn_VOLT_reg_high/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.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": "9cbf12825f7307ff244f39fc9e0b10ad9a4ce8a6b851a9fcd417771811d6dd3d", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The road turns left behind the bridge.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "e6cc6750f406e987831063d3f5d75dcfd9b1f1953134771d3da0d5446a70353a", "generation_seconds_batch": 15.75652514200192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7277473211288452, "target_z": -1.1015625155496251, "ce": 6.252951145172119, "genuineness": 3.9425034523010254, "identity": 0.2209639996290207, "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/vn_VOLT_reg_high/9cbf12825f7307ff244f39fc9e0b10ad9a4ce8a6b851a9fcd417771811d6dd3d.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "9d0083d30fc83c4ff6d3aaf7b46320097a7cabcb643606347a843b9d3e55f440", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 129, "seconds_generated": 10.32, "mp3_sha256": "235f2f42df7eee6d22251314673fa16e051d00ea3a89dd50e44cffdc3711740c", "generation_seconds_batch": 21.870387542061508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6911916732788086, "target_z": 0.007812612064539292, "ce": 5.990842819213867, "genuineness": 4.068024158477783, "identity": 0.7326680421829224, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient ?", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9d0083d30fc83c4ff6d3aaf7b46320097a7cabcb643606347a843b9d3e55f440.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "9d541926b975d73f888548cc63d45ff8b92d525f3aae603a97f9e68cd8907c66", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "992bb75ae12ace1de29a4dc97ea98efea864650c2409806ae2a46caa735a3ee2", "generation_seconds_batch": 21.553226838004775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6870384216308594, "target_z": -1.148437501608582, "ce": 6.252951145172119, "genuineness": 4.369274139404297, "identity": 0.598069429397583, "hypothesis": "Ik 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/vn_VOLT_reg_high/9d541926b975d73f888548cc63d45ff8b92d525f3aae603a97f9e68cd8907c66.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "9d6bc4b7a07f8cbe837216864ea57c1c7ac2001282f1e89c376a41a2c91d08d4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9d4f3240b569c068c68ee23e42be41a38f6e13d09170e68fedf0cd96109f2686", "generation_seconds_batch": 19.797196412924677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4918875694274902, "target_z": -0.22167964158839149, "ce": 5.982900142669678, "genuineness": 3.9173994064331055, "identity": 0.5323970913887024, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9d6bc4b7a07f8cbe837216864ea57c1c7ac2001282f1e89c376a41a2c91d08d4.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "9dceea85033785c9d4a9c3d73e9fb1ac6f437661028e7eb45969b4099e6835bf", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c4baf539e5e6fa2632589544ab95381fd48be1d32d9c904b9924ce2a15d694d9", "generation_seconds_batch": 19.724668285925873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8227348327636719, "target_z": -0.9921874565682886, "ce": 6.229123115539551, "genuineness": 4.18099308013916, "identity": 0.49951645731925964, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9dceea85033785c9d4a9c3d73e9fb1ac6f437661028e7eb45969b4099e6835bf.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "9df06ad1e830566e2da3e1f2b2174e76be9ea8ec439bd08ec9176f304a64e4b5", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0a26ef8da9aad9ce707855e4fd2ad6a0a7aa4ef3ca490bea544fc86201fa47b2", "generation_seconds_batch": 19.797196412924677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.246785879135132, "target_z": -0.5039063403486836, "ce": 5.967014789581299, "genuineness": 3.8420867919921875, "identity": 0.26213788986206055, "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/vn_VOLT_reg_high/9df06ad1e830566e2da3e1f2b2174e76be9ea8ec439bd08ec9176f304a64e4b5.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "9df11c52e0cfb722e89c8a9479000d142adde6afeaae74e99199b8bb18bf38c4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "96e323a3d913185958e07e713d34d34156343fc763cee92cbaceaba6450c2396", "generation_seconds_batch": 21.07562426000368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5300521850585938, "target_z": -0.177734316420809, "ce": 6.070269584655762, "genuineness": 4.118232727050781, "identity": 0.5336216688156128, "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/vn_VOLT_reg_high/9df11c52e0cfb722e89c8a9479000d142adde6afeaae74e99199b8bb18bf38c4.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": "9e2408454cac79e6062e344759b2aa612b1b45320f914273d9d4ecb6ecbe0aa3", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c9359bf25ac533f3436e542c4f2f27675532dae23209b340661d206be97ea5d", "generation_seconds_batch": 17.59566766198259, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8363044261932373, "target_z": -0.9765625069705216, "ce": 5.847874641418457, "genuineness": 4.030367851257324, "identity": 0.2248033881187439, "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/vn_VOLT_reg_high/9e2408454cac79e6062e344759b2aa612b1b45320f914273d9d4ecb6ecbe0aa3.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "9e2b9b18225816ebd91b628921919ef6e6b1602b73d478de78e3a44268b3b75d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "aad581a0f800029fb05260df741bbecda9113c45925bdd359391ae3e6153d8e3", "generation_seconds_batch": 21.756857234053314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8498740196228027, "target_z": -0.9609375573727545, "ce": 6.197352409362793, "genuineness": 4.118232727050781, "identity": 0.4205072522163391, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9e2b9b18225816ebd91b628921919ef6e6b1602b73d478de78e3a44268b3b75d.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": "9e3a5cd8fb6e058a0afbdb732cce43d8bb67dff13b1ed3625a0f6ceeffbadf60", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9c72c2d26ed523803569a71a380956208ca6653efbb191e35edda46e9c2055a", "generation_seconds_batch": 13.673370586009696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5537989139556885, "target_z": -0.15039072325754463, "ce": 6.038498878479004, "genuineness": 4.105680465698242, "identity": 0.608160138130188, "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/vn_VOLT_reg_high/9e3a5cd8fb6e058a0afbdb732cce43d8bb67dff13b1ed3625a0f6ceeffbadf60.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "9e65df6dee5a2af7d0a60b7e21cba56a51c44052a454b09e6c6aa720028c4f2a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e67ea973f0d2180410736d51ba64a5b3adbf9b5ad9dadcc98d443026cc7ecf7a", "generation_seconds_batch": 19.39918376202695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.673468828201294, "target_z": -1.1640624512063489, "ce": 6.125868320465088, "genuineness": 4.344170093536377, "identity": 0.5506099462509155, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9e65df6dee5a2af7d0a60b7e21cba56a51c44052a454b09e6c6aa720028c4f2a.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "9ea053ee0efce339c6779e68d0c8fcb14f49afd2f940e83f91d15a2500551453", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd72cd99793bca32950faa9abea50c346da46226dd9b27dcc861579dfe898c09", "generation_seconds_batch": 14.491837114910595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8396968841552734, "target_z": -0.9726562009382519, "ce": 5.935244083404541, "genuineness": 4.419482707977295, "identity": 0.6840448379516602, "hypothesis": "La porte 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/vn_VOLT_reg_high/9ea053ee0efce339c6779e68d0c8fcb14f49afd2f940e83f91d15a2500551453.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "9f44ac8dbc8e476d1bf96471cb4b03dd00e666fe7976b0fa0ef3b57dc7ee0529", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b03368a053703a63cd13a79e5c4dff28aaf603be99b2aeeb34c77c855b74c420", "generation_seconds_batch": 21.653953721979633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3138734102249146, "target_z": -1.5781249882037327, "ce": 6.340320587158203, "genuineness": 4.306513786315918, "identity": 0.5289149284362793, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9f44ac8dbc8e476d1bf96471cb4b03dd00e666fe7976b0fa0ef3b57dc7ee0529.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "9f5b241dc8ead832d0e7d5e6226cce715884e6e458cf38c2ed168de477286eab", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "361c8c5164f6c4a9ee81676fa89ab10d0e5b0ba6639aa3980dc6052e04c9cc26", "generation_seconds_batch": 21.748338041943498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.033064126968384, "target_z": -0.7500000514746209, "ce": 6.157639026641846, "genuineness": 4.68307638168335, "identity": 0.6113452911376953, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/9f5b241dc8ead832d0e7d5e6226cce715884e6e458cf38c2ed168de477286eab.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": "9fcd267bf27f1f15cd355e736e656cf3646ab7b3b27036ef6d69420db26b0d94", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The keys are on the kitchen table.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f26ba5e4ee51105947a07480c46c40ff754466db825331d6ce8c3858b6910683", "generation_seconds_batch": 14.627948652021587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2942795753479004, "target_z": -0.44921887949084327, "ce": 6.173524379730225, "genuineness": 3.760498285293579, "identity": 0.5834589004516602, "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/vn_VOLT_reg_high/9fcd267bf27f1f15cd355e736e656cf3646ab7b3b27036ef6d69420db26b0d94.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "a02243376aaf93daff0d475260c5711a3658da80f733914a575a592f5f5fe4f0", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "033e9d3d404b7623ae304eb0fba8cc1a825502249f7bd4645d64d2df3a2ca37d", "generation_seconds_batch": 15.034934246912599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6463295221328735, "target_z": -1.1953124876675387, "ce": 6.149696350097656, "genuineness": 4.243753433227539, "identity": 0.5797377228736877, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a02243376aaf93daff0d475260c5711a3658da80f733914a575a592f5f5fe4f0.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "a0e642c6472d21cbf8f418383b7c919e8d9c624fb3c64a90afeb7cacdd982bf4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "abf9e3c61b582bf2c4ddfa5bbb8520e4de4bb8f7232fed7144b63163a75f52f3", "generation_seconds_batch": 19.829309803899378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.491800308227539, "target_z": 0.9296876581772205, "ce": 5.780362129211426, "genuineness": 3.6192874908447266, "identity": 0.5682289600372314, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a0e642c6472d21cbf8f418383b7c919e8d9c624fb3c64a90afeb7cacdd982bf4.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "a0eeacfebde2148b729b9f6d44ec6f61d357fe7886ae5f4f4009d505b561b605", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b4bb9a4f3cd097a56218a8e3e13a9d20c187e2353468b270a622705b4f7a523b", "generation_seconds_batch": 16.1133835259825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.58526611328125, "target_z": -1.2656250353888019, "ce": 6.1020402908325195, "genuineness": 4.545003414154053, "identity": 0.5699965953826904, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a0eeacfebde2148b729b9f6d44ec6f61d357fe7886ae5f4f4009d505b561b605.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "a10cf883bb71d754d43083a9efcba8bd0b75c2f530a5728155a48acb8fcfcb5a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b6e80836a08c0692d56452cddd760b89e1be4d5a48ab74d7f01df2d6dca7e1bf", "generation_seconds_batch": 14.762510615051724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8159499168395996, "target_z": -1.0000000686328279, "ce": 6.038498878479004, "genuineness": 4.432034492492676, "identity": 0.6922012567520142, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a10cf883bb71d754d43083a9efcba8bd0b75c2f530a5728155a48acb8fcfcb5a.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "a13a9186733d69f7de9d5464cd92bbafe84a26ac4af757ffe6462519b537db28", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6d88a8e6299336b18b6205013e23e2f1cf181d91e8f15d3853fcb6bda58fae0d", "generation_seconds_batch": 21.665578585932963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9855704307556152, "target_z": -0.8046875123324613, "ce": 6.0146708488464355, "genuineness": 4.306513786315918, "identity": 0.3001394271850586, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a13a9186733d69f7de9d5464cd92bbafe84a26ac4af757ffe6462519b537db28.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "a1c0892c030360a1264e47744b52eb400a3ec1d38b22bfbba46c20af7c3223d2", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "70ebb0048518cac5837914723fb3e4874838f585f23fa4b8b2519cbb1a79d282", "generation_seconds_batch": 14.931279892916791, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0161020755767822, "target_z": -0.7695313071046576, "ce": 6.316492557525635, "genuineness": 4.758388519287109, "identity": 0.38121092319488525, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a1c0892c030360a1264e47744b52eb400a3ec1d38b22bfbba46c20af7c3223d2.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "a20931f4edaaec44336dab8a83871ea444d3436b66d8571e1476a8bc2399f81f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4cabbd6bacc83b91951ec36d389234ef3e9ff68901ad14a29894afd0a33ec45b", "generation_seconds_batch": 22.059162570978515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5113937854766846, "target_z": -0.19921886233263628, "ce": 5.685050010681152, "genuineness": 4.319066047668457, "identity": 0.6277464628219604, "hypothesis": "La porte 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/vn_VOLT_reg_high/a20931f4edaaec44336dab8a83871ea444d3436b66d8571e1476a8bc2399f81f.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "a2ee12927727c9adcb85a922c617bc8141946ea2868cdbd5fedfbbf1ec4f0908", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ba5393404bd4474657268e42d12f524b8cf11dabef07463bd9cf31c6ae09c14e", "generation_seconds_batch": 19.822016085963696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2731645107269287, "target_z": -1.6249999742626895, "ce": 6.078212261199951, "genuineness": 3.7040140628814697, "identity": 0.30985042452812195, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a2ee12927727c9adcb85a922c617bc8141946ea2868cdbd5fedfbbf1ec4f0908.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "a324cdd1afd0c95491d4e6784d03b5913c075df15415aa57552f643ca40a02de", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fe8004f8e805ed938b9f8c3bb5add99ace3d6297bc4ce635ac7adb3da2c450fd", "generation_seconds_batch": 21.617526735994034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9584312438964844, "target_z": -0.8359374115279953, "ce": 6.316492557525635, "genuineness": 4.419482707977295, "identity": 0.5059739947319031, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a324cdd1afd0c95491d4e6784d03b5913c075df15415aa57552f643ca40a02de.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "a32cee9d822846efacc52e49289c32b86c175293fb7220e0c4209ebcfeab7de0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7eb87a42708f8e4bef742110b7a47071c774b62e1a05a575e412beae1c69fada", "generation_seconds_batch": 21.498521744972095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9507107734680176, "target_z": 0.30664049376652636, "ce": 5.784333229064941, "genuineness": 4.005263805389404, "identity": 0.5618176460266113, "hypothesis": "La porte 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/vn_VOLT_reg_high/a32cee9d822846efacc52e49289c32b86c175293fb7220e0c4209ebcfeab7de0.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "a3346ca0887644cb0d76386fc4dd4f6db2768567aec9bde7ec69b993af1192f4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bce2381ac432b1f125a94a1f3191854d37a97ded8360350937e79da3ca4c01e8", "generation_seconds_batch": 20.158709567971528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.948253870010376, "target_z": -0.8476563296248042, "ce": 6.316492557525635, "genuineness": 4.243753433227539, "identity": 0.5408270359039307, "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/vn_VOLT_reg_high/a3346ca0887644cb0d76386fc4dd4f6db2768567aec9bde7ec69b993af1192f4.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "a34ff60ad0fb513712eb810aa7b3f25d7c8b5d2ec0610e957810e0208fc19891", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4906b9fe906a5df2016b15ff9950a0e31bd40fda61addacdfa166c591bd29283", "generation_seconds_batch": 21.992718623019755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9075450897216797, "target_z": -0.8945311784181053, "ce": 6.197352409362793, "genuineness": 4.256305694580078, "identity": 0.3344024121761322, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a34ff60ad0fb513712eb810aa7b3f25d7c8b5d2ec0610e957810e0208fc19891.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "a3546e2f0a7ad6a60579099d1f2122a25008534cf3426ddcb9b9e361f35862c5", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "695d90239eb7b8d1cb4c20b1703f47f234874a2d5e403ed871387cbd874b8dd3", "generation_seconds_batch": 21.629279676941223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302760601043701, "target_z": -0.43945325167582494, "ce": 5.998785495758057, "genuineness": 3.873466968536377, "identity": 0.6827009916305542, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a3546e2f0a7ad6a60579099d1f2122a25008534cf3426ddcb9b9e361f35862c5.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "a35770aa022f7de52c786fa7e70a2412d48997dd589c3c5385883ce44581baf3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bc708cd1b2ab5c87e98d0cf1c8462464dc16bc9e53fb748671a797a07d63ded0", "generation_seconds_batch": 20.138115223962814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9550387859344482, "target_z": -0.839843717560265, "ce": 6.308549880981445, "genuineness": 4.331617832183838, "identity": 0.5168832540512085, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a35770aa022f7de52c786fa7e70a2412d48997dd589c3c5385883ce44581baf3.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": "a388569c25c633bd758e86db29bfb123213c2368a6a23b613f5dcbf6dbfd0411", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The road turns left behind the bridge.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "731b48ff408ce3fa33cc2bd0f4f0187caeb6c7e85bc0d352b8480fe7917e1f8d", "generation_seconds_batch": 23.278354109963402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.094127655029297, "target_z": -0.679687366487702, "ce": 6.38003396987915, "genuineness": 3.7793264389038086, "identity": 0.47339171171188354, "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/vn_VOLT_reg_high/a388569c25c633bd758e86db29bfb123213c2368a6a23b613f5dcbf6dbfd0411.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "a3fe43321457f02d4c81f4d3ea073ea6dcf664b977cee6e3d3bd618b54257eaa", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "ac022e6e1788f6e0aa109588d21eeecb955feff3111aa02d30bf2ce4bf9e52b2", "generation_seconds_batch": 21.76834372803569, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5377724170684814, "target_z": -1.3203124962466422, "ce": 6.372091293334961, "genuineness": 4.105680465698242, "identity": 0.5644428730010986, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinaus.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a3fe43321457f02d4c81f4d3ea073ea6dcf664b977cee6e3d3bd618b54257eaa.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "a427a325ca4d12c9a8d706b269237833bea28029d85d1b76cf658dac5c5d8f24", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "31e9875fe4015b15da954c7a790a9304f8463c114ba01158ba40d90061e1dc87", "generation_seconds_batch": 15.805396878975444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.254331588745117, "target_z": 0.6562500793567072, "ce": 5.839932441711426, "genuineness": 3.47493839263916, "identity": 0.6582144498825073, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a427a325ca4d12c9a8d706b269237833bea28029d85d1b76cf658dac5c5d8f24.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "a43b5f78519a82f6f686f8a2c00bd4ba1605155a24d3c319877e3bc8a2c319dc", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "8518853ba9a03f2381f587309c1a53c68b92669bf463ee7f57251ab26c94d972", "generation_seconds_batch": 19.852179751032963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.491039514541626, "target_z": -0.22265614946363102, "ce": 6.054384231567383, "genuineness": 4.231201171875, "identity": 0.5974973440170288, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a43b5f78519a82f6f686f8a2c00bd4ba1605155a24d3c319877e3bc8a2c319dc.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "a47555973f68dad766ede4ece3c552a1f7f7a884bb8f1615e0034e805ed1463f", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f8d9d47acca167a47dee013047f2e723a017852afe1a16544ee710f58b863435", "generation_seconds_batch": 15.239451398025267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8837981224060059, "target_z": -0.9218750461126812, "ce": 6.197352409362793, "genuineness": 4.6956281661987305, "identity": 0.6711026430130005, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a47555973f68dad766ede4ece3c552a1f7f7a884bb8f1615e0034e805ed1463f.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": "a4a0c6017464de47b18130002d050304d596186731235d89195a7ec17ebde951", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "09a448bced9d2ed639077a553254e97db66f4a5e1bc7be077ded5f68ad2aa7a9", "generation_seconds_batch": 14.788210667087696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348558187484741, "target_z": -0.38671880656846364, "ce": 6.213237762451172, "genuineness": 4.325342178344727, "identity": 0.5093787908554077, "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/vn_VOLT_reg_high/a4a0c6017464de47b18130002d050304d596186731235d89195a7ec17ebde951.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "a4c64fc891140116ff0c57ae7545235fce12a8c0417a6d6f7a6f2e4173644024", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "64b3a8d957bb45589791eaf9fe9ba5cfd26d04b26426bd33e9cd6e1cfbecc13b", "generation_seconds_batch": 22.19284234091174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.066988229751587, "target_z": -0.7109375402145476, "ce": 5.5539960861206055, "genuineness": 4.049196243286133, "identity": 0.47639498114585876, "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/vn_VOLT_reg_high/a4c64fc891140116ff0c57ae7545235fce12a8c0417a6d6f7a6f2e4173644024.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "a4eb3ec4757f7a921fc696bbd9fcc2542f0059a516b1b572de66930b76c781d3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c9441a8ddeaeca5d72fca8c5c891db248621abfdf6c9b9ea040ff3298864c264", "generation_seconds_batch": 14.575587228988297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2976720333099365, "target_z": -0.4453125734585736, "ce": 6.117925643920898, "genuineness": 4.1998209953308105, "identity": 0.2650606036186218, "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/vn_VOLT_reg_high/a4eb3ec4757f7a921fc696bbd9fcc2542f0059a516b1b572de66930b76c781d3.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "a5566026abf9232b95d019f4fe972a96f5df054748f08c66eb94a95b4a5e0d98", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2adc46534f52cb980c163d9e9b69afd4c5574b4937e7a2d394b2662eb3b92c16", "generation_seconds_batch": 17.11846595897805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9686083793640137, "target_z": -0.8242187679624979, "ce": 5.919358730316162, "genuineness": 3.9299514293670654, "identity": 0.6114999055862427, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a5566026abf9232b95d019f4fe972a96f5df054748f08c66eb94a95b4a5e0d98.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "a58a682de7f2c0f021300ae9d182a5ae7ebffa53814443cbe3023ec1978f3045", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1db6c81da72f8a7b5d42adaee468e310251bc9db2168fc9f57d67f4fa286bd3d", "generation_seconds_batch": 21.17097608698532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7242674827575684, "target_z": 0.04589834091806153, "ce": 6.078212261199951, "genuineness": 3.9425034523010254, "identity": 0.7352805733680725, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a58a682de7f2c0f021300ae9d182a5ae7ebffa53814443cbe3023ec1978f3045.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "a58b7ba77403f351fd752eac8b465b6a6e829ae48ad030d33badcc8dc249448f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f7a8f3899fb2d866b7617716dd7f1d87fa84dfd5ecc19efabd685645f114df5", "generation_seconds_batch": 20.7752492739819, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.018558979034424, "target_z": 0.384765516286673, "ce": 5.673136234283447, "genuineness": 3.427868366241455, "identity": 0.37001800537109375, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a58b7ba77403f351fd752eac8b465b6a6e829ae48ad030d33badcc8dc249448f.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": "a64571b4d6db707f7c93cecf5613a5510b070c4dec0b59e2876ceb1035a69004", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "4a850d654dc7ee66b488c8ea3a0094060be153d778438a8552c764c73711c897", "generation_seconds_batch": 20.212786489981227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4740774631500244, "target_z": -0.24218740509366768, "ce": 5.6334228515625, "genuineness": 4.111956596374512, "identity": 0.6470507383346558, "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": 0.120000000000001, "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/vn_VOLT_reg_high/a64571b4d6db707f7c93cecf5613a5510b070c4dec0b59e2876ceb1035a69004.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "a82e1382d413335dda2ecd21abb237d62ba2255a27da9fa5a249d5b3f2939915", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a93a757b233ea70f9bf43cc107ad6d53e4496d22a98ef44f2e2166f15060af06", "generation_seconds_batch": 14.97009151999373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5038483142852783, "target_z": -1.3593750075067155, "ce": 5.982900142669678, "genuineness": 3.7667744159698486, "identity": 0.31642311811447144, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a82e1382d413335dda2ecd21abb237d62ba2255a27da9fa5a249d5b3f2939915.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "a866eb7222fe73e654b4139f4322de97d2631f502347d71c2fa3f4ba6a39520a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ca21c5f64fff7928f21c1dd401a54105c75472afaa55227610a4a1dba15f6b2a", "generation_seconds_batch": 22.510580510017462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.429975986480713, "target_z": -0.29296883445054994, "ce": 6.022613525390625, "genuineness": 3.873466968536377, "identity": 0.2473156750202179, "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/vn_VOLT_reg_high/a866eb7222fe73e654b4139f4322de97d2631f502347d71c2fa3f4ba6a39520a.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "a86a5256dd7704ed86243bfccd9db0a3c37bc4d9ccb198d5264cf9a46c8baada", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "91c530111229ccd430d8a5670dd9f004fbfc9b4647a342fe4957f6812bd624e0", "generation_seconds_batch": 22.475107604055665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.002532482147217, "target_z": -0.7851562567024246, "ce": 5.355429172515869, "genuineness": 3.898571252822876, "identity": 0.4817744493484497, "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/vn_VOLT_reg_high/a86a5256dd7704ed86243bfccd9db0a3c37bc4d9ccb198d5264cf9a46c8baada.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "a88e560eb1ef8d399b3bcfa75760eea37392170b9da4ac35566039212b247cb3", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b6246427c4895fffac4443f48a85ae325e6044172de9958f59ba6112b0d44bc6", "generation_seconds_batch": 15.242842889972962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9814172983169556, "target_z": -1.9609374887399267, "ce": 6.292664527893066, "genuineness": 3.9299514293670654, "identity": 0.3795589804649353, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a88e560eb1ef8d399b3bcfa75760eea37392170b9da4ac35566039212b247cb3.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "b44a4c7e9f63cb3dd47569e8c2f6f66ac1a80275e6ff52ded74aac286802d7e7", "generation_seconds_batch": 15.744588024914265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3206582069396973, "target_z": -1.5703125134048492, "ce": 6.054384231567383, "genuineness": 4.174716949462891, "identity": 0.7415390610694885, "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/vn_VOLT_reg_high/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.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": "a8f9e3123d137ce6642b4e952d182b274cc6d5e259aa52b9b199c76fb4799fcc", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f910b1606934fdd7e81a6498b6827fc28d09b02db1d34eb1cc4de5173d50ee0", "generation_seconds_batch": 21.544400686980225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.04909086227417, "target_z": 0.4199219960457882, "ce": 6.0146708488464355, "genuineness": 4.011539936065674, "identity": 0.5717185735702515, "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/vn_VOLT_reg_high/a8f9e3123d137ce6642b4e952d182b274cc6d5e259aa52b9b199c76fb4799fcc.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "a91df16aa38becbd1a0e028d4909ed8ca4b474cbe1039051dc92e339125b5e47", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c95e10a72bcc2bf3806e25a1f7cb0a8423bc558178d20a8630359f69cc94877a", "generation_seconds_batch": 20.84233006404247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5581269264221191, "target_z": -1.296874934584336, "ce": 5.605623245239258, "genuineness": 3.8922953605651855, "identity": 0.6287764310836792, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a91df16aa38becbd1a0e028d4909ed8ca4b474cbe1039051dc92e339125b5e47.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "a932f6e1381fcae1fd58246e034360ca4e27e12beafa8bfef39f0c735a79893d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8e354560e8fea75b4b3621d3981201b6d604ce1bf575faf3f7824a083f51d51b", "generation_seconds_batch": 20.408677516970783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3621277809143066, "target_z": -0.3710938569706966, "ce": 6.133810997009277, "genuineness": 4.055472373962402, "identity": 0.4885881543159485, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a932f6e1381fcae1fd58246e034360ca4e27e12beafa8bfef39f0c735a79893d.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "a94035c6e0213944d5bf337038e7ac8d2f4fa2bb5c712d731369a985f9d31ac8", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "315e405378391f306eb312fdd72c7566c1f420f100581cd799f2acbda7c772e2", "generation_seconds_batch": 21.37899062805809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9863312244415283, "target_z": 0.34765629530839026, "ce": 6.086154937744141, "genuineness": 3.503180742263794, "identity": 0.514945387840271, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a94035c6e0213944d5bf337038e7ac8d2f4fa2bb5c712d731369a985f9d31ac8.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "bdedd1a527cafb6777402d1849316e0909ef33f40a1fe71b0a0c83adc253ddd4", "generation_seconds_batch": 17.536195621010847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7481017112731934, "target_z": -1.0781250911529745, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.8163986206054688, "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/vn_VOLT_reg_high/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.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": "a983b9ed386c6d19a298552198c3b5d912f21694020bc7076fa014bf972332f7", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I wrote the number on the envelope.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "d894692703992483023d85df61c494bf71789e6195f707757286803fea39159e", "generation_seconds_batch": 14.84915618703235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0602035522460938, "target_z": -0.7187498777477753, "ce": 6.1894097328186035, "genuineness": 4.017816066741943, "identity": 0.34210875630378723, "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/vn_VOLT_reg_high/a983b9ed386c6d19a298552198c3b5d912f21694020bc7076fa014bf972332f7.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "a9982b3d67ecdcdd3d3228497c5c549beea6d3f4c0a29a2d957c96226832b55e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "57bf0f9d1b23b683ec6853c5b36aed914bb1ee105210c7470c2e1f27d4928fc2", "generation_seconds_batch": 22.16098135802895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.284102439880371, "target_z": -0.4609375230563406, "ce": 6.006728172302246, "genuineness": 3.8546390533447266, "identity": 0.7434549927711487, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/a9982b3d67ecdcdd3d3228497c5c549beea6d3f4c0a29a2d957c96226832b55e.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "aa1ab23abf76c226aad74eeaba8f6abcbe91ddf6cc9643c521bb6cd6f2d45ee1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "14487bf70474b8adf27663c419d2e1eee33d7b005376807c44e356de70d92c4e", "generation_seconds_batch": 15.803797219065018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.850634813308716, "target_z": 0.191406250268097, "ce": 6.022613525390625, "genuineness": 4.074300289154053, "identity": 0.5877803564071655, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijkers.", "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/vn_VOLT_reg_high/aa1ab23abf76c226aad74eeaba8f6abcbe91ddf6cc9643c521bb6cd6f2d45ee1.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "aa2b4446e23816fbe676a93eea5c9a18243c9a9e21adfd27c1723f2c0a8a6b7d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5cf21437de7f39bd2f6f755f600ab131ae848af833e2d25a8d89287bf374338e", "generation_seconds_batch": 20.158709567971528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9109374284744263, "target_z": -0.8906250096514914, "ce": 6.149696350097656, "genuineness": 3.9927117824554443, "identity": 0.5251441597938538, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/aa2b4446e23816fbe676a93eea5c9a18243c9a9e21adfd27c1723f2c0a8a6b7d.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "aa6e2b3de005b6754db96699d9d01c50ed8cc013345c13fa2c62b1a65d0cd574", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "91b43fcb1be1f17063fcf8fdb21ca504f4b8216ce0d9758e34b8fa7ec824923b", "generation_seconds_batch": 22.09997738606762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.161975860595703, "target_z": -0.6015623439675554, "ce": 6.0146708488464355, "genuineness": 3.8546390533447266, "identity": 0.241567462682724, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/aa6e2b3de005b6754db96699d9d01c50ed8cc013345c13fa2c62b1a65d0cd574.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "ab0f45026a93b4db4571cadd9e569eb8199ecf77770bbd775a10a3fa37630def", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "eb1a552f1539c5afef2c4032aca9c6cda32dd4c648dadf32e2cca83f78cbb359", "generation_seconds_batch": 21.28922697994858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6191902160644531, "target_z": -1.2265625241287286, "ce": 6.197352409362793, "genuineness": 3.7416701316833496, "identity": 0.38941940665245056, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ab0f45026a93b4db4571cadd9e569eb8199ecf77770bbd775a10a3fa37630def.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": "ab2fbf3a1a815be9d3b102705ad85003672360eaa7142bead58ca13893fe762d", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e5bf0d9cae848c54c5e350f2e564fb9f23823909bbdb499c7b2e78ef7ac113eb", "generation_seconds_batch": 21.708768471027724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.033064126968384, "target_z": -0.7500000514746209, "ce": 6.046441555023193, "genuineness": 3.936227321624756, "identity": 0.4958455562591553, "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/vn_VOLT_reg_high/ab2fbf3a1a815be9d3b102705ad85003672360eaa7142bead58ca13893fe762d.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7502bfb8195b1705581e04f1f9130eff6752d625a8e76c18bd07e1c2aa7d33b8", "generation_seconds_batch": 15.190722496947274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.734532117843628, "target_z": -1.0937500407507417, "ce": 6.443574905395508, "genuineness": 4.2374773025512695, "identity": 0.24555739760398865, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "abe052b3c7746e4f4aeadc919ccd53d80cf6a8689c5063ea39da9b1ae3c932ba", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "32680065eda52b6d5e5ecd0f89953a8a164415d688565ecc0e8b8fae4d1bd61b", "generation_seconds_batch": 20.898361123050563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2026846408843994, "target_z": -0.5546874951742543, "ce": 5.871703147888184, "genuineness": 4.20609712600708, "identity": 0.5610294342041016, "hypothesis": "La porte 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/vn_VOLT_reg_high/abe052b3c7746e4f4aeadc919ccd53d80cf6a8689c5063ea39da9b1ae3c932ba.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "ac25561f648f7e186dfff7f83b017ec109769b83d9617641eda75cb8305d9dd4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "95870868a55ae3605f5ad8ea2662a02c24231364a3d0fa45a4b0d16b54c8beec", "generation_seconds_batch": 16.41749071003869, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.7156991958618164, "target_z": 1.1875000128686553, "ce": 5.7684478759765625, "genuineness": 3.7291181087493896, "identity": 0.08682975172996521, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ac25561f648f7e186dfff7f83b017ec109769b83d9617641eda75cb8305d9dd4.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "ac2cb639165c090c2136b7bc17da4918fb5e8bf318dd891a2334aba0603414f4", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f8531dc7f9f9983ed642243f8cb83d37a151236d03535a9e0db8a725d0400150", "generation_seconds_batch": 14.80648051307071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2460252046585083, "target_z": -1.6562500107238793, "ce": 5.959072113037109, "genuineness": 4.042920112609863, "identity": 0.6004007458686829, "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/vn_VOLT_reg_high/ac2cb639165c090c2136b7bc17da4918fb5e8bf318dd891a2334aba0603414f4.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "ac4437bd68fe1dc0cfbcf09c4f1102f0ffd5b8db22af42845ecc233758ff7620", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0f0ad375b6f1ba92bb5718f4a048a5a05756345eabcce72759be7dd6f56c546", "generation_seconds_batch": 21.078369597904384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0296716690063477, "target_z": -0.7539063575068906, "ce": 5.597680568695068, "genuineness": 4.024092197418213, "identity": 0.5349161624908447, "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/vn_VOLT_reg_high/ac4437bd68fe1dc0cfbcf09c4f1102f0ffd5b8db22af42845ecc233758ff7620.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "ac694f5e3c2714a59fb5fd16209fc1bab6c7d4d0abae1a085595981e3b5cb089", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "00d14ce338120042a5320a9456146fb8d215a22d5293e237bab217187580b4d1", "generation_seconds_batch": 21.598714953986928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1423821449279785, "target_z": 0.5273439020109899, "ce": 5.831989288330078, "genuineness": 3.7542223930358887, "identity": 0.46510130167007446, "hypothesis": "De duur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ac694f5e3c2714a59fb5fd16209fc1bab6c7d4d0abae1a085595981e3b5cb089.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "ac939340c44e160ecd92452894c86c6698e5ab1074760a5fe130885a6411c429", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ab8e38465b78180e387e6d95405014394e2a98d9e8e078fbb23df87a35a3e693", "generation_seconds_batch": 20.94663986598607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3315961360931396, "target_z": -0.4062500621985003, "ce": 6.022613525390625, "genuineness": 4.2249250411987305, "identity": 0.515982985496521, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. ¡Vieja! Pudimos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ac939340c44e160ecd92452894c86c6698e5ab1074760a5fe130885a6411c429.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "acddf00084f661962cba5fb896db5ed2ae8f2db7a374adeddfdd78049ae68e04", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5edf15219aeec2d4da0ebcf98c69fb4c24255c9617762e934048e67976e69de9", "generation_seconds_batch": 14.80027357803192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.510633111000061, "target_z": -1.351562532707832, "ce": 5.613565921783447, "genuineness": 3.7542223930358887, "identity": 0.4914088249206543, "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/vn_VOLT_reg_high/acddf00084f661962cba5fb896db5ed2ae8f2db7a374adeddfdd78049ae68e04.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "acfe9ccc362cce5ff6ee20371e6fe18dcf1a817f686b9a44be608c19ea22d6a9", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "627557f30f5f29f86df2560f41c3810deb41718ae097b149c8e14795b6a2b1ff", "generation_seconds_batch": 15.587706797989085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6666839122772217, "target_z": -1.1718750632708883, "ce": 6.197352409362793, "genuineness": 4.319066047668457, "identity": 0.18792802095413208, "hypothesis": "The door is still open. I put your coat on the chair. How me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/acfe9ccc362cce5ff6ee20371e6fe18dcf1a817f686b9a44be608c19ea22d6a9.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "ada4a96dc2cde906621c460cdcecdc0972b0e6a47af43f4082ec9ccf55748d64", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "346465645d82a09af8835a88f4a9a35ff89d2603dadd82b925eb7814c3565af5", "generation_seconds_batch": 21.528232307056896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7522549629211426, "target_z": 0.07812502252014665, "ce": 5.911416053771973, "genuineness": 3.9801597595214844, "identity": 0.7097089886665344, "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/vn_VOLT_reg_high/ada4a96dc2cde906621c460cdcecdc0972b0e6a47af43f4082ec9ccf55748d64.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "adc428d120af0d69fd549fe90de524b3a49f82b54d1633786e8485f8ae685ff7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9863dc2cfe3c750bd9adfb5e17b03016882d4a686ff2bc96d49b6b8eb23fd247", "generation_seconds_batch": 22.70179081801325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.32744300365448, "target_z": -1.5625000386059658, "ce": 6.284721851348877, "genuineness": 3.8546390533447266, "identity": 0.39678525924682617, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/adc428d120af0d69fd549fe90de524b3a49f82b54d1633786e8485f8ae685ff7.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "0fea085762c1f590e8402f9e3d33b7812059f2055462f5d53e0d181da2ec61d0", "generation_seconds_batch": 16.560262896004133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9346842765808105, "target_z": -0.8632812792225713, "ce": 6.23706579208374, "genuineness": 4.394378662109375, "identity": 0.7676321268081665, "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/vn_VOLT_reg_high/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "ade73c26bae2d724bb85e99f19c29eba2fc3a030e569e9891548553994baaea2", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "cb2cddd8ae337840646ac6f5acf7fa077499f23c44c3d10fb0d9d72106fc50b6", "generation_seconds_batch": 21.10749418591149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2298238277435303, "target_z": -0.5234375959787203, "ce": 5.935244083404541, "genuineness": 4.074300289154053, "identity": 0.5655084848403931, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ade73c26bae2d724bb85e99f19c29eba2fc3a030e569e9891548553994baaea2.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "adf66d064fe04c8f996662a853cb063d6cbce9618b1e3b6fe0ed24d50b9f83e2", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5eb0d1f35b652546d8011f23c22808fcfeb7a535e45ea3b06118346c39c0b016", "generation_seconds_batch": 22.19284234091174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.161975860595703, "target_z": -0.6015623439675554, "ce": 5.395142555236816, "genuineness": 3.8044304847717285, "identity": 0.4700813591480255, "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/vn_VOLT_reg_high/adf66d064fe04c8f996662a853cb063d6cbce9618b1e3b6fe0ed24d50b9f83e2.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "bc5737402e58862441f2b51eab79e365be40d9a0250f8129e0077285399da272", "generation_seconds_batch": 15.29633338097483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4970635175704956, "target_z": -1.3671874823055992, "ce": 6.332377910614014, "genuineness": 3.923675537109375, "identity": 0.4477255940437317, "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/vn_VOLT_reg_high/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "ae331641d35fd721355a72c704c38e50fad5086db4c103dec4ad6b04446c8000", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00e21ef93c6049509adabaa2c84a0cf412544376334348f7acf0e8c0e2b7fa89", "generation_seconds_batch": 21.492408100049943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5920509099960327, "target_z": -1.2578125605899184, "ce": 6.09409761428833, "genuineness": 4.457139015197754, "identity": 0.676401674747467, "hypothesis": "La porte 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/vn_VOLT_reg_high/ae331641d35fd721355a72c704c38e50fad5086db4c103dec4ad6b04446c8000.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": "ae3c425e2fbb4b617aa6fbce9ac17e39f361125618e750401b68e325798fd5a7", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The keys are on the kitchen table.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "998bcf98e174aa8448b219a5ba3789833f2ac5c8ea3f5e70646204ea650ca405", "generation_seconds_batch": 14.627948652021587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.314634084701538, "target_z": -0.42578131782853695, "ce": 6.149696350097656, "genuineness": 3.9425034523010254, "identity": 0.5441457033157349, "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/vn_VOLT_reg_high/ae3c425e2fbb4b617aa6fbce9ac17e39f361125618e750401b68e325798fd5a7.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "ae55b3c2d5ccdea50435037a7031e51a9ecff16dc1cde0d20ef64251372611f4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c466f2ea15ba754fa6c4ae1e529e4f76411d9f8bcd1ee32efc920abc07bdc356", "generation_seconds_batch": 20.924085226026364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.122027635574341, "target_z": 0.5039063403486836, "ce": 5.645336627960205, "genuineness": 3.8797430992126465, "identity": 0.5712020993232727, "hypothesis": "La porte 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/vn_VOLT_reg_high/ae55b3c2d5ccdea50435037a7031e51a9ecff16dc1cde0d20ef64251372611f4.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": "ae5d04e1a5595444e03a2e6b0afeb60997f3ae4db209f2fbd82035862ce8f698", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "72c327a8dc77bd756571298f5e563dedb1b6f322c71e4b04f83381b05d839862", "generation_seconds_batch": 13.673370586009696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2026846408843994, "target_z": -0.5546874951742543, "ce": 5.863759994506836, "genuineness": 4.093128204345703, "identity": 0.6135153770446777, "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/vn_VOLT_reg_high/ae5d04e1a5595444e03a2e6b0afeb60997f3ae4db209f2fbd82035862ce8f698.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "ae63cdb596a60470210ab80e626015635abe11541552aebdb8be5dcbda0268a3", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "db0d720c9d225d7c2b449081256356f0d1816d6e4702ee13733ca13d5480aaf3", "generation_seconds_batch": 16.20551031793002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3138734102249146, "target_z": -1.5781249882037327, "ce": 6.022613525390625, "genuineness": 4.068024158477783, "identity": 0.6234978437423706, "hypothesis": "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/vn_VOLT_reg_high/ae63cdb596a60470210ab80e626015635abe11541552aebdb8be5dcbda0268a3.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "af2636429e0f7daafcd8c088bb6db11711381df6efe8ace8c287124ff5ce7eec", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "65a261459627563fbade11924cda01d824ecaa6e1eaa2f2822da73371dc2e74d", "generation_seconds_batch": 21.63147620402742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.495192527770996, "target_z": 0.9335936896781786, "ce": 5.816103935241699, "genuineness": 3.4623863697052, "identity": 0.38648682832717896, "hypothesis": "Ik 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/vn_VOLT_reg_high/af2636429e0f7daafcd8c088bb6db11711381df6efe8ace8c287124ff5ce7eec.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": "afdd747752af23bf6a57dd636e579b241f98ec1dfd1762c6f0c7210ad4ee6836", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "648fc2386613d49ec9183573c6e956710009d508fb40c2598d60ea2093a90383", "generation_seconds_batch": 21.277879680041224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8905830383300781, "target_z": -0.9140624340481419, "ce": 5.95112943649292, "genuineness": 3.9550557136535645, "identity": 0.8392834067344666, "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/vn_VOLT_reg_high/afdd747752af23bf6a57dd636e579b241f98ec1dfd1762c6f0c7210ad4ee6836.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "b073741ca8e1c59dc5901e6ccbfc73376dcb3c967bc9ebea420c01a53cf2ca4e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a0a782d41f33daf2c87a2f21f3161e34c668790abb22a8bac3b1a8d949fa8769", "generation_seconds_batch": 16.08103142597247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1382288932800293, "target_z": -0.6289062116621313, "ce": 6.022613525390625, "genuineness": 4.017816066741943, "identity": 0.22419404983520508, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b073741ca8e1c59dc5901e6ccbfc73376dcb3c967bc9ebea420c01a53cf2ca4e.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": "b0793deff4ace959174d93e0f83ce904123707785152533b57987b1d178a7acd", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c493bfac0c2e525dee6f24e1ce435788613f596c4665b729183c6f5ed8ed789e", "generation_seconds_batch": 15.022433908074163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.195899724960327, "target_z": -0.5625001072387936, "ce": 6.117925643920898, "genuineness": 4.13078498840332, "identity": 0.41257816553115845, "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/vn_VOLT_reg_high/b0793deff4ace959174d93e0f83ce904123707785152533b57987b1d178a7acd.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "b127b3608f6e80fb82c66b9811b5249fcd5d5428d6bf00afbf310b0bad5abae3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bab519793075af8cfb5a25bcd953d5cee72ba92652b6ff116b2bac3bb16b3fbd", "generation_seconds_batch": 21.09063850506209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.734532117843628, "target_z": -1.0937500407507417, "ce": 6.23706579208374, "genuineness": 4.362998008728027, "identity": 0.6559430956840515, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b127b3608f6e80fb82c66b9811b5249fcd5d5428d6bf00afbf310b0bad5abae3.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "b130899893570519d30a2ab3f19a3d99958d5c9ae10973b7278d5a60f0537581", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b867a36cbed57565b0ed30a67f68e3f9b08e728f179cd9b3fdeae4619b297acf", "generation_seconds_batch": 21.947675788076594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9041526317596436, "target_z": -0.898437484450375, "ce": 6.348263263702393, "genuineness": 4.545003414154053, "identity": 0.6270391941070557, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b130899893570519d30a2ab3f19a3d99958d5c9ae10973b7278d5a60f0537581.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "b1a810a7b3ac13fcbf0c0b54633f6be42a578295808759944524a1729b7352a7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8dd5f2361e5c580ff575f19094589d2123ef491c66a41186bf50953a2a724566", "generation_seconds_batch": 22.39383153000381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3010644912719727, "target_z": -0.44140626742630396, "ce": 6.125868320465088, "genuineness": 3.5941832065582275, "identity": 0.6095770597457886, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b1a810a7b3ac13fcbf0c0b54633f6be42a578295808759944524a1729b7352a7.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "b1ccac95d190983fa0fb8884bca5be37cc93a3bfaa7a9294e52f56b1ad9d7f88", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a27e483b0b6900e0590c765682499691d5115cc1d7a9b2ac60376cfb0526d814", "generation_seconds_batch": 21.507710578036495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2366087436676025, "target_z": -0.515624983914181, "ce": 6.260893821716309, "genuineness": 4.344170093536377, "identity": 0.7425935864448547, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b1ccac95d190983fa0fb8884bca5be37cc93a3bfaa7a9294e52f56b1ad9d7f88.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "b1e61cbc534c9eea9b73bd30b3429e5aa3dd4ee477ae90309832b3fc0419fd13", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f75acd610990708c060277ae0dcdf78b9d21f115f4717dfa9144978450c0a5d3", "generation_seconds_batch": 21.342964345938526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6056206226348877, "target_z": -1.2421874737264955, "ce": 6.316492557525635, "genuineness": 4.281409740447998, "identity": 0.5122184753417969, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b1e61cbc534c9eea9b73bd30b3429e5aa3dd4ee477ae90309832b3fc0419fd13.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "b1ebdef4fcf26c1623b5f5ade9c7a364660e1f819c6a63b2a0d4568ecaad4e03", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "311363dc63dfc47aa396bc3d7b85f26110ad52d176a3e0d6c5f88bb9c52dc631", "generation_seconds_batch": 15.943135960027575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.178176999092102, "target_z": -1.734375033244026, "ce": 6.157639026641846, "genuineness": 4.193545341491699, "identity": 0.6645618677139282, "hypothesis": "La porte 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/vn_VOLT_reg_high/b1ebdef4fcf26c1623b5f5ade9c7a364660e1f819c6a63b2a0d4568ecaad4e03.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "b22bb0c8f58bc4594d6ff40ec1e682b32ff215b96ffcaa35b30ecb7f5fbc8608", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85a93fc4c7cb25d9746cc9b9588b5f800e6bbe5c8c46efc0a9630c798ef19cee", "generation_seconds_batch": 15.583915262017399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4224305152893066, "target_z": -1.4531249796246293, "ce": 6.23706579208374, "genuineness": 4.325342178344727, "identity": 0.5735896825790405, "hypothesis": "La porte 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/vn_VOLT_reg_high/b22bb0c8f58bc4594d6ff40ec1e682b32ff215b96ffcaa35b30ecb7f5fbc8608.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "b232bf02e13d5200571b9265586362cd36bc9a5b877e72686ff34817d4f060bd", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8657fa62ce44b76ef7e13fccedec78e448884fa35299db70a4c61d38e4dc8365", "generation_seconds_batch": 21.06881698104553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8905830383300781, "target_z": -0.9140624340481419, "ce": 5.808161735534668, "genuineness": 4.068024158477783, "identity": 0.5700653195381165, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b232bf02e13d5200571b9265586362cd36bc9a5b877e72686ff34817d4f060bd.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": "b274c41e9554350f64b283f6ed39bfbbfa4ca32616739b0ca5cf3bfc60b7d93f", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe030fcaddbf053d160af335cb044337cea10a27bcc5ed8585a2f17b8671a4d3", "generation_seconds_batch": 13.569872471038252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.433368444442749, "target_z": -0.2890625284182803, "ce": 5.847874641418457, "genuineness": 3.9927117824554443, "identity": 0.5827898383140564, "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/vn_VOLT_reg_high/b274c41e9554350f64b283f6ed39bfbbfa4ca32616739b0ca5cf3bfc60b7d93f.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "b296c4e350d98a4194eee14de3b71d6ff0be7ad6393a8935b979a53d4168f31b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "65aadb3f75c5233bc202d9d9479a88c4df2d62ef7f00fb04cff509bd1e759d1d", "generation_seconds_batch": 19.649951436091214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6056206226348877, "target_z": -1.2421874737264955, "ce": 6.205295085906982, "genuineness": 4.632867813110352, "identity": 0.5128768682479858, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b296c4e350d98a4194eee14de3b71d6ff0be7ad6393a8935b979a53d4168f31b.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "b29724f94315f41592f0937f4263950269d124221f2e9de5de1b365a8f6f564b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "db00b9ef7f14cdb0c2e82c69a553fef5c268244f451c4eaaa94809ea34a5c906", "generation_seconds_batch": 23.471899840049446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1450138092041016, "target_z": -0.621093599597592, "ce": 6.141753673553467, "genuineness": 4.344170093536377, "identity": 0.5469003319740295, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b29724f94315f41592f0937f4263950269d124221f2e9de5de1b365a8f6f564b.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "b37f279c477c0709936009f3e3ef36ec750be4fddfebb95279204f1a06a4f3a4", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6d648435ec109dcf7ef0100d696c07de6cfc6625fb855d918a69bd17edfcca24", "generation_seconds_batch": 15.67618605797179, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6666839122772217, "target_z": -1.1718750632708883, "ce": 6.38797664642334, "genuineness": 4.545003414154053, "identity": 0.4891156256198883, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b37f279c477c0709936009f3e3ef36ec750be4fddfebb95279204f1a06a4f3a4.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "b3d576f16833d3572ea9ac16dd2b1e7da1ee9b97d5b3e048b35cc96dee6f72fd", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "16f0ad60b0bfd53db8a421cc608c4a817f080c0a2dacbbd8bfa87385ea07038f", "generation_seconds_batch": 16.18445148295723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2433934211730957, "target_z": -0.5078126463809532, "ce": 6.1020402908325195, "genuineness": 4.036643981933594, "identity": 0.45070064067840576, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b3d576f16833d3572ea9ac16dd2b1e7da1ee9b97d5b3e048b35cc96dee6f72fd.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "b3ffed50ac98f912815df9ad3bcdf13ea568b15dc9342944f44c9c790867e952", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f802372394c3a034d2c1e78cb859f45f3eb88c81f9eaaefd0ead9dc5c66698a4", "generation_seconds_batch": 20.43929201492574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6463295221328735, "target_z": -1.1953124876675387, "ce": 6.141753673553467, "genuineness": 4.256305694580078, "identity": 0.44854170083999634, "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/vn_VOLT_reg_high/b3ffed50ac98f912815df9ad3bcdf13ea568b15dc9342944f44c9c790867e952.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "d6108288718502a29a22cb317215dd6ced0a3da7e3b4c56403403ab8e816ba2a", "generation_seconds_batch": 13.480389957898296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.1894097328186035, "genuineness": 4.293961524963379, "identity": 0.6771417856216431, "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/vn_VOLT_reg_high/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "b4348b445cbf9f2b3562ba9aa90b2d8417e97032e0d184a8a7423804e2de7d9a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c973ed5777bac0c9756681fbfed4c32de0a62e85a395d1c230e9203bdaf480c0", "generation_seconds_batch": 21.598714953986928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.335749387741089, "target_z": 0.7500000514746209, "ce": 5.486483573913574, "genuineness": 3.6349775791168213, "identity": 0.20573028922080994, "hypothesis": "De deur 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/vn_VOLT_reg_high/b4348b445cbf9f2b3562ba9aa90b2d8417e97032e0d184a8a7423804e2de7d9a.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "b51743e4b7917a76a4e9ca16438d9d4238356cac43de34456a5289648484b1ba", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4ee2583d8a003ebfa714b63014de16de298f5bc5a135fb09027f537338936be5", "generation_seconds_batch": 15.67618605797179, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4088608026504517, "target_z": -1.468750066488052, "ce": 6.38797664642334, "genuineness": 4.030367851257324, "identity": 0.5074551105499268, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b51743e4b7917a76a4e9ca16438d9d4238356cac43de34456a5289648484b1ba.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "b51aaa9cf9b5454afce98994149b1315fb9a5ad64808925c2f8901d74683a05d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1ac30dfc77c8aa3bbf2335b73b29980c66dd6d088916e430170c5b96118ad2a0", "generation_seconds_batch": 21.05814796197228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3129379749298096, "target_z": -0.42773433357901597, "ce": 6.086154937744141, "genuineness": 3.7793264389038086, "identity": 0.6906349062919617, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b51aaa9cf9b5454afce98994149b1315fb9a5ad64808925c2f8901d74683a05d.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "b632b74c738ba4a1eedaf043dcc6b13eff3b36c14b8692f24afe23fac7fe7f2c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "412f811e6cec2185881612cb2301972b09347e80faa9403621c6eab3c8ea888b", "generation_seconds_batch": 15.357947338954546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5649117231369019, "target_z": -1.2890624597854523, "ce": 6.062326908111572, "genuineness": 4.381826400756836, "identity": 0.782381534576416, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b632b74c738ba4a1eedaf043dcc6b13eff3b36c14b8692f24afe23fac7fe7f2c.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "b68f474e567b29d55977df0b3220eba9847a7a485df031a2a1f163ec485847d2", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3769e64f081ddd7e6c79772ac58dcfd99fc3e00bbbf5415627850efda8fe0ac1", "generation_seconds_batch": 14.677422499051318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.09409761428833, "genuineness": 4.250029563903809, "identity": 0.7170153856277466, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b68f474e567b29d55977df0b3220eba9847a7a485df031a2a1f163ec485847d2.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "b76ee2994f601729b611b7b5cef949954b689fdefcdf1391abd99967139b7942", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bb19059b36bd0560382d6476a391759de27db2672dcfb1b8600ace0723bfd060", "generation_seconds_batch": 21.40668079594616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4808621406555176, "target_z": -0.23437506756043996, "ce": 5.109206199645996, "genuineness": 3.6287014484405518, "identity": 0.4439760744571686, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lindo.", "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/vn_VOLT_reg_high/b76ee2994f601729b611b7b5cef949954b689fdefcdf1391abd99967139b7942.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "b79079db210331230dad7b8d5db32c04354bf12c28eae348650072c1b9f6be1e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "94b8fff05e105add0d314767b681784bc233482230e0767a707436247d236fba", "generation_seconds_batch": 20.171180142904632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.260893821716309, "genuineness": 4.118232727050781, "identity": 0.5908492803573608, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b79079db210331230dad7b8d5db32c04354bf12c28eae348650072c1b9f6be1e.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "b83abe5b021c672d838af952e290aaf6cd41a96074e01659b54bd0108a678978", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53b6da8c68afd2c7736c2117eea4b5dc3980174e65a802d8ce9faeec543575cd", "generation_seconds_batch": 21.993132918025367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6056206226348877, "target_z": -1.2421874737264955, "ce": 6.157639026641846, "genuineness": 4.049196243286133, "identity": 0.5342535972595215, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b83abe5b021c672d838af952e290aaf6cd41a96074e01659b54bd0108a678978.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "b83d88a02b2554da779cb5b47403f5fb4d2d9f8b9353055a2e1ab0c90e4a6483", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "36805d3879945a479606d6e4b2791a5a3424493d0f2e9ad541eb9b661811145d", "generation_seconds_batch": 20.926643955986947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.162736415863037, "target_z": 0.5507811891419846, "ce": 5.792276382446289, "genuineness": 3.540836811065674, "identity": 0.6764664053916931, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b83d88a02b2554da779cb5b47403f5fb4d2d9f8b9353055a2e1ab0c90e4a6483.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "b876162fac6c9ae13d25f086a01e81a4f887dcb61e5cc7254ad861e9c677ffc4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "407cef6bd561bf1b09316c06cdbe11da38fd81fddaf9ede78f3dbc5039cc43cb", "generation_seconds_batch": 20.426635609008372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9744577407836914, "target_z": 0.33398436146110233, "ce": 5.879645347595215, "genuineness": 3.5314228534698486, "identity": 0.7044273018836975, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b876162fac6c9ae13d25f086a01e81a4f887dcb61e5cc7254ad861e9c677ffc4.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "b8c8cfbed9706b715a97c98c6ae00d9f8127148a8111d7f5b0200edf291c6c9a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "39d688a7e099155ef9147b0216cc928282c906fc84de979d7729f4d12bcec1dc", "generation_seconds_batch": 19.736094641964883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.707392930984497, "target_z": -1.1249999399462756, "ce": 6.062326908111572, "genuineness": 4.344170093536377, "identity": 0.601386547088623, "hypothesis": "La porte 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/vn_VOLT_reg_high/b8c8cfbed9706b715a97c98c6ae00d9f8127148a8111d7f5b0200edf291c6c9a.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": "b8ed5508b2856e2aaa4d312e31430730c45b5bce6365b173c362eb80879690bc", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b53ea810f1d41591bd04f29a546c351c7fc219d529905422c3b48c78d67191b", "generation_seconds_batch": 13.61783776897937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.747166395187378, "target_z": 0.07226570073739796, "ce": 5.9431867599487305, "genuineness": 3.8044304847717285, "identity": 0.5592345595359802, "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/vn_VOLT_reg_high/b8ed5508b2856e2aaa4d312e31430730c45b5bce6365b173c362eb80879690bc.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "b97464cb1e58f53525affa85b216f41fcbfc030cf3460564bd5ccaada9e3ce98", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "271459d9fc4ca35e8a7423ee00a157ad15bf15161cb0cc478529fdc66fd721cf", "generation_seconds_batch": 21.406064387992956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1823301315307617, "target_z": -0.5781250568365606, "ce": 6.157639026641846, "genuineness": 4.099404335021973, "identity": 0.7724958062171936, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b97464cb1e58f53525affa85b216f41fcbfc030cf3460564bd5ccaada9e3ce98.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "b98cd96db4d3e0acee9c23a661224fa6311ff18f1fc671a9bd43fd29e3598afb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a050e35b286e49c537179fd96cf8099ceefbd33607a47d44a3b40645bf997393", "generation_seconds_batch": 14.867085897945799, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.799748659133911, "target_z": 0.13281248337798698, "ce": 5.990842819213867, "genuineness": 4.118232727050781, "identity": 0.08419843763113022, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay detrás.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b98cd96db4d3e0acee9c23a661224fa6311ff18f1fc671a9bd43fd29e3598afb.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": "b999b4649c012c97327020f35a6c6682689dd151bb428932dc06f87bc211b734", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ecd9d450bce70c17008cf7bb2f81e77864bc57abe2c71e3ac61ac26eb492bf9e", "generation_seconds_batch": 14.231758348061703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.66235613822937, "target_z": -0.02539057741278535, "ce": 6.268836498260498, "genuineness": 4.149612903594971, "identity": 0.6303330063819885, "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 participes.", "wer": 0.041666666666666664, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/b999b4649c012c97327020f35a6c6682689dd151bb428932dc06f87bc211b734.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": "ba264020f08e032ee379e05df186e2a2873c11dd1615e8a0f1dd32e5ab884861", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29496391a6585c567cc768167e5ee1951a19d2e41d8d8528b12959b123d9a9ad", "generation_seconds_batch": 21.843643672997132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8955843448638916, "target_z": 0.24316418750021876, "ce": 5.871703147888184, "genuineness": 3.7793264389038086, "identity": 0.6752034425735474, "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/vn_VOLT_reg_high/ba264020f08e032ee379e05df186e2a2873c11dd1615e8a0f1dd32e5ab884861.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "ba6d60631cf49e080050910b31fee7e11e5d0f6ced4a72ec05a3b460829051a9", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3c14c507981f8c805ed351b3c5094549f7b819f1ec0144dee4b6c7d2a56e2eea", "generation_seconds_batch": 20.370200339937583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1355972290039062, "target_z": 0.5195312899464506, "ce": 6.149696350097656, "genuineness": 3.9299514293670654, "identity": 0.6561581492424011, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ba6d60631cf49e080050910b31fee7e11e5d0f6ced4a72ec05a3b460829051a9.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "ba709f81e9379293830ad6cefe0a6daf344516f686cb0e493bca3a5aff3586bb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "065d6b9e19d6f69b1cb2aba465a65475120c787ef471c5e14a3e4ca13fa0f795", "generation_seconds_batch": 21.456864006002434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.851395606994629, "target_z": 1.3437500579089485, "ce": 5.621508598327637, "genuineness": 3.603597402572632, "identity": 0.5396111011505127, "hypothesis": "La porte 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/vn_VOLT_reg_high/ba709f81e9379293830ad6cefe0a6daf344516f686cb0e493bca3a5aff3586bb.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "1049a5ab9a74a8a0adb5e69a48391cb2c9e8736d0cfbe2949514458c07b110b6", "generation_seconds_batch": 16.459339090040885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.436000108718872, "target_z": -1.437500030026862, "ce": 6.109982967376709, "genuineness": 4.645420074462891, "identity": 0.6275946497917175, "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/vn_VOLT_reg_high/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "bb8d663921dc11666bfb131995f431a774a5196527101c46899087b6645dcdcf", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "47aba6f1898b23ce56dced84bf16ea5192617c39dcc2da34c1f06e70b11ddd0e", "generation_seconds_batch": 16.21279080293607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4970635175704956, "target_z": -1.3671874823055992, "ce": 5.506340026855469, "genuineness": 4.099404335021973, "identity": 0.6540968418121338, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás limita.", "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/vn_VOLT_reg_high/bb8d663921dc11666bfb131995f431a774a5196527101c46899087b6645dcdcf.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "bbba259774b527b57b91abacc9d21e3dfdca94e6c9c4f5b95a4065970a75cf80", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "26a8152c38adcfc80fa966448c64900c2a86bcdfc6a6aae520875ccb593bf869", "generation_seconds_batch": 15.646908047026955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7277473211288452, "target_z": -1.1015625155496251, "ce": 5.80021858215332, "genuineness": 4.042920112609863, "identity": 0.4957946240901947, "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/vn_VOLT_reg_high/bbba259774b527b57b91abacc9d21e3dfdca94e6c9c4f5b95a4065970a75cf80.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "bbda47f5d56f1304ce31b6a572a39444e45e48f8bed6f3588385f40763d57297", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69428a311844ddc21e43838a1ca452b4634ae96a1381e47c55b339d4f0e4ea1a", "generation_seconds_batch": 15.112159300944768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2908873558044434, "target_z": -0.45312491099180136, "ce": 6.165581703186035, "genuineness": 4.080576419830322, "identity": 0.3903244733810425, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bbda47f5d56f1304ce31b6a572a39444e45e48f8bed6f3588385f40763d57297.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "bc19534a961a8011e20b1ebc119e22e4f45f5c84a59036c7e7731ff025677f27", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "82d7f5d096f61922efc53315a59f9dac8a12d2f68521212f09837862ddcbed68", "generation_seconds_batch": 15.506394125986844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7548866271972656, "target_z": -1.0703124790884353, "ce": 6.09409761428833, "genuineness": 4.143336772918701, "identity": 0.6838897466659546, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bc19534a961a8011e20b1ebc119e22e4f45f5c84a59036c7e7731ff025677f27.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "bc60f974d6957e2c2175b7d9dd1d11590ba39ed57821d044a4e125a79b14ab66", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1369dc0b5db45ebbb8f7660dc66b0380d66f88df955257597a1bffaf7c8976f", "generation_seconds_batch": 20.70558362803422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.32744300365448, "target_z": -1.5625000386059658, "ce": 5.982900142669678, "genuineness": 4.18099308013916, "identity": 0.5572602152824402, "hypothesis": "La porte était encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bc60f974d6957e2c2175b7d9dd1d11590ba39ed57821d044a4e125a79b14ab66.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "bc6bd5b65657855163b67e7c9e821352e651f4c7288c9cf5e04649318b0b1daa", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7527c773286e943b785444a84ac39106f98b5b9b4ad35307cf3f9f262cd3eefa", "generation_seconds_batch": 20.693806312978268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.399444341659546, "target_z": -0.3281250396783536, "ce": 6.0305562019348145, "genuineness": 4.055472373962402, "identity": 0.43401607871055603, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bc6bd5b65657855163b67e7c9e821352e651f4c7288c9cf5e04649318b0b1daa.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "bca0cf9237efcf313672fb618b7628fdaccf7d168efaa20f2644cec372799b2f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3be0c3448d843ac1624f67373f5eb9bf2fd3f03762076e54a2ed24048ad33bf7", "generation_seconds_batch": 15.629513395950198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8192551136016846, "target_z": 0.1552735371650538, "ce": 6.0305562019348145, "genuineness": 3.773050308227539, "identity": 0.43496453762054443, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bca0cf9237efcf313672fb618b7628fdaccf7d168efaa20f2644cec372799b2f.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "bcc663476da718f2d9a5f9657626ae223fc1b7f3b60880fb81df8c71e916fd2c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "927043c29b4ec7ef59e2ee6bc4b8c8e53a5132165bc17732552e4dbcc57106dd", "generation_seconds_batch": 20.653726221062243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.158583402633667, "target_z": -0.605468649999825, "ce": 5.959072113037109, "genuineness": 3.8546390533447266, "identity": 0.5439019203186035, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bcc663476da718f2d9a5f9657626ae223fc1b7f3b60880fb81df8c71e916fd2c.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": "bcc7e1e5d32233a9d60fceaf7b8cbea2057b2a47ef5f9b6f67d908a6d7540816", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Someone moved the little blue chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "83d75498c7f99b2e60c14950732cd6404c081daf0f955a9f05c61ccb0cc8c7b0", "generation_seconds_batch": 15.504482486983761, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.615710496902466, "target_z": -0.07910153039538617, "ce": 6.221180438995361, "genuineness": 4.13078498840332, "identity": 0.39927077293395996, "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/vn_VOLT_reg_high/bcc7e1e5d32233a9d60fceaf7b8cbea2057b2a47ef5f9b6f67d908a6d7540816.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "bcd5c1eb9415a537183b79dc80a08031e045e8679631904c29816e9cd8bc7fc1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8d42f28e0f6899668034682ccba85e4cabf6c025610576f9157eddac8d59b147", "generation_seconds_batch": 14.867085897945799, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.668205499649048, "target_z": 1.132812552010815, "ce": 5.617537498474121, "genuineness": 3.760498285293579, "identity": 0.39652085304260254, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay detrás.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bcd5c1eb9415a537183b79dc80a08031e045e8679631904c29816e9cd8bc7fc1.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "bcd6b5287dd5e4d69a4c056746638c730b2bf4c5412350c59d032f6bfda9a083", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "41dad9e86d428b7f170d0ed8a34d521aee9f7b51a10924ed9af3e7f7188aa60a", "generation_seconds_batch": 20.65286208607722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.189115047454834, "target_z": -0.5703124447720213, "ce": 6.09409761428833, "genuineness": 4.281409740447998, "identity": 0.5853383541107178, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bcd6b5287dd5e4d69a4c056746638c730b2bf4c5412350c59d032f6bfda9a083.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "bd3f9a3683346d586a5dbb194115b80a5e19abad13b302276bd79b04a156985f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19008343e7da7afadfd92525ec5d4df2578489b5a601fb89d5e605f3786b41bb", "generation_seconds_batch": 15.623499669949524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0194945335388184, "target_z": -0.765625001072388, "ce": 5.998785495758057, "genuineness": 4.105680465698242, "identity": 0.6556182503700256, "hypothesis": "La porte 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/vn_VOLT_reg_high/bd3f9a3683346d586a5dbb194115b80a5e19abad13b302276bd79b04a156985f.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "bd43d325756f202fb811bb3a05cc636f2e100e9c81bdc95e105dc6bb7923ffb1", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ef56bf8fb7f5319974389eaf3d26036fd09b6080114bad1bd383136e6cd9d4dc", "generation_seconds_batch": 14.652993898023851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2867341041564941, "target_z": -1.6093750246649225, "ce": 6.062326908111572, "genuineness": 4.13078498840332, "identity": 0.43897297978401184, "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/vn_VOLT_reg_high/bd43d325756f202fb811bb3a05cc636f2e100e9c81bdc95e105dc6bb7923ffb1.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": "bd6557701f1fcc0d1fbb6c065d8a7f1f032d5dd46cf7ab40cac215d01ef21f54", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "22b322aede1013d9af80df751ff6df787391596ea21e92c49f92e83a33b86c28", "generation_seconds_batch": 20.919981223065406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.045698404312134, "target_z": 0.4160156900135186, "ce": 5.831989288330078, "genuineness": 4.13078498840332, "identity": 0.6158878803253174, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis c'est rangé mon téléphone. Dis-moi quand nous pourrons parler ?", "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/vn_VOLT_reg_high/bd6557701f1fcc0d1fbb6c065d8a7f1f032d5dd46cf7ab40cac215d01ef21f54.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "bd876e425dbfe38937382587eed3bd8e6422a90fd934bba3f7827b85cba1cea1", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0b2975c024161f167ce3a0f7379c55efb7a737af15be6a525c5bbf971aa2cd2d", "generation_seconds_batch": 16.018694182974286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4970635175704956, "target_z": -1.3671874823055992, "ce": 6.2767791748046875, "genuineness": 4.607763767242432, "identity": 0.568657398223877, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bd876e425dbfe38937382587eed3bd8e6422a90fd934bba3f7827b85cba1cea1.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": "bdd382d9be2106e587bdee6140e29756731a77d20f3dac194473177c83da47fc", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8f9a4f52886e0d1a5ccabb64cfc4a5c4c706052347ff868a81edaefe1b326ed7", "generation_seconds_batch": 20.346773423952982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6068053245544434, "target_z": -0.08935554941368004, "ce": 6.09409761428833, "genuineness": 3.8922953605651855, "identity": 0.3235040307044983, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bdd382d9be2106e587bdee6140e29756731a77d20f3dac194473177c83da47fc.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "bdead2c4e33c59caa1819ac945860423d6535aaefe4b50660c7a3929906b7f5b", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "255c1b46d1d251a761139a4628e1735c6c743f50c097d890d7f416ef8a45d91f", "generation_seconds_batch": 15.616046765004285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6531143188476562, "target_z": -1.1875000128686553, "ce": 6.268836498260498, "genuineness": 4.494794845581055, "identity": 0.6893160343170166, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bdead2c4e33c59caa1819ac945860423d6535aaefe4b50660c7a3929906b7f5b.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "be22a697d1abd9497cac9d44e8c2752376c829b38bcfa30e7f5620a3890e9cc8", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1d400261a59a24ee083f8ce90de9cdcd3afafeee7f23a3f703f07991056ce8eb", "generation_seconds_batch": 15.292809414095245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4427849054336548, "target_z": -1.4296875552279786, "ce": 6.173524379730225, "genuineness": 4.6705241203308105, "identity": 0.7418539524078369, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/be22a697d1abd9497cac9d44e8c2752376c829b38bcfa30e7f5620a3890e9cc8.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "be72b17d521315583f57e9ee5bc20077c0365c0368343ec644390ae0043f1d14", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "55ad43df574226830df7642fde679243ea2693b85d8e49b0a416d1b9fac708c0", "generation_seconds_batch": 15.908738080062903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.598835825920105, "target_z": -1.249999948525379, "ce": 6.205295085906982, "genuineness": 4.432034492492676, "identity": 0.7396941184997559, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/be72b17d521315583f57e9ee5bc20077c0365c0368343ec644390ae0043f1d14.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "be7d073be6b3319295da561d38d5f3aeb3448f6423e2e7ccf913c3449afa84d3", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "77439fd6d88070997d9d6ba17467c2703cf548394651378f962f70fcb31a330a", "generation_seconds_batch": 20.819428190006875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.631824493408203, "target_z": -0.06054678264058903, "ce": 5.808161735534668, "genuineness": 3.923675537109375, "identity": 0.7180849313735962, "hypothesis": "La porte 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/vn_VOLT_reg_high/be7d073be6b3319295da561d38d5f3aeb3448f6423e2e7ccf913c3449afa84d3.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": "bea956c8f4efb0dcff6421048be404706223cc8a6c74f3f34d1903f3a49a8f63", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04949ef3384c33ee74d360bc115926a10e5e407b5402f8ba876b2b95dcc40994", "generation_seconds_batch": 20.919981223065406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.960888147354126, "target_z": 0.3183594118633353, "ce": 5.879645347595215, "genuineness": 4.162164688110352, "identity": 0.7059510946273804, "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/vn_VOLT_reg_high/bea956c8f4efb0dcff6421048be404706223cc8a6c74f3f34d1903f3a49a8f63.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "beb5f6ea2346a5cec2abe0bbe2a4b9f58e7e18c62d6951508f6450664b207f41", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3307259447ba764de44a37ecd4fe18268dd204ecaced1f4ceefea6d0f7ebcdf6", "generation_seconds_batch": 21.40997720195446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.178176999092102, "target_z": -1.734375033244026, "ce": 6.2767791748046875, "genuineness": 4.080576419830322, "identity": 0.5183649063110352, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/beb5f6ea2346a5cec2abe0bbe2a4b9f58e7e18c62d6951508f6450664b207f41.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "befba87c46085d8cac0258d2a3af54fe417f6e7bd3f0f32b21aef02d27912b63", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b209871231393f0241ed171ac17962299ca1ea1d65eda606d2e82e5d1af2543f", "generation_seconds_batch": 22.069488772074692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4631394147872925, "target_z": -1.4062499935656725, "ce": 6.24500846862793, "genuineness": 4.356721878051758, "identity": 0.5260534286499023, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/befba87c46085d8cac0258d2a3af54fe417f6e7bd3f0f32b21aef02d27912b63.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "befbc9b6f030543daa51fa82ad4fcc3104947f3d3e075e1514704235675d0027", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7d8553718b1f5e5044024bdd41b03256bc9ad324452824148534bad604e2563a", "generation_seconds_batch": 21.72804333898239, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1823301315307617, "target_z": -0.5781250568365606, "ce": 5.685050010681152, "genuineness": 4.105680465698242, "identity": 0.31225860118865967, "hypothesis": "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/vn_VOLT_reg_high/befbc9b6f030543daa51fa82ad4fcc3104947f3d3e075e1514704235675d0027.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "bf6a63e873795facd7f646d3b6b0d1e798a49cfcd29d70aa5dfb1fdb32fe1055", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b8c4201b0486c647515e04725b1a49fb326c292e06e4363750f1a78d4438a226", "generation_seconds_batch": 20.885774613008834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.415645718574524, "target_z": -1.4609374544235127, "ce": 6.141753673553467, "genuineness": 4.262581825256348, "identity": 0.6905401945114136, "hypothesis": "La porte 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/vn_VOLT_reg_high/bf6a63e873795facd7f646d3b6b0d1e798a49cfcd29d70aa5dfb1fdb32fe1055.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "bfccd497fdfbdb54cdc0726924aca9026016663b011c933e684738352af00eee", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3b6ae63991e0540e416cb518360b14f30ac4986fc43f5246d42e2d52b29dae16", "generation_seconds_batch": 20.31556551810354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.149696350097656, "genuineness": 4.519899368286133, "identity": 0.7548703551292419, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bfccd497fdfbdb54cdc0726924aca9026016663b011c933e684738352af00eee.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "bfd46a40550618f0196c01b22d01d94e0e9af0457db4ff41f610f2876ae62a7c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9a272ba56e1e9b3b3d3ac7dc5574809e43bff66d8bd312e22a4957a76eb1159e", "generation_seconds_batch": 21.807995823095553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5174179077148438, "target_z": -1.3437500579089485, "ce": 6.38003396987915, "genuineness": 4.344170093536377, "identity": 0.5034806132316589, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bfd46a40550618f0196c01b22d01d94e0e9af0457db4ff41f610f2876ae62a7c.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "bffac7c72adf9856858937481029bda03641b8888c6f22dbe88e321cf3e93599", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8e9d75005ed9db10ee4fb92afb6e782bd8bbc47887acf2b93ee7faabdd3ce3ff", "generation_seconds_batch": 22.08692156802863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.948253870010376, "target_z": -0.8476563296248042, "ce": 5.998785495758057, "genuineness": 3.9801597595214844, "identity": 0.6863250732421875, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/bffac7c72adf9856858937481029bda03641b8888c6f22dbe88e321cf3e93599.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "c01d18bfafbe9c9f72f2414810946f8be362571640ba36eff27ca74ed5ed8712", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "780b1a332cf17c0b2ce10d93d16f91f6d2032bd93183a837b057ba5543878450", "generation_seconds_batch": 20.205279950983822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.659899115562439, "target_z": -1.1796875380697718, "ce": 6.149696350097656, "genuineness": 3.8420867919921875, "identity": 0.42691144347190857, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c01d18bfafbe9c9f72f2414810946f8be362571640ba36eff27ca74ed5ed8712.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "c0225f3c5ad9c7b9513fe09175a768805d7866ce88896188cbbb013c3c5b8ef0", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "606a4735d5241b4c53801ad37d837c02a4392ee6843a18b3702e625eddf84190", "generation_seconds_batch": 16.587533309939317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2256708145141602, "target_z": -1.67968743512053, "ce": 6.4515180587768555, "genuineness": 4.055472373962402, "identity": 0.4717170000076294, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c0225f3c5ad9c7b9513fe09175a768805d7866ce88896188cbbb013c3c5b8ef0.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "c03432dd1e1c2f0e4440adb65e618eb8c8b048f3bbc9cc42c5adb02492995882", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b17b7116d0dc20c015f0cc115dd2144db16774f81a05b9f33838c0a5629a55ba", "generation_seconds_batch": 20.51092041202355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4435458183288574, "target_z": -0.27734361032147137, "ce": 5.847874641418457, "genuineness": 4.105680465698242, "identity": 0.20487596094608307, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c03432dd1e1c2f0e4440adb65e618eb8c8b048f3bbc9cc42c5adb02492995882.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": "c0f34e4767b330820a486ab72440fd19aa00cddd34d5d9e4f058de7ad2ba4ede", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "6058f5b599789e0c4fc659ea5c5dff55968f75eafa4eb85eaffde1d282cc8429", "generation_seconds_batch": 15.899518066085875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7413170337677002, "target_z": -1.0859374286862022, "ce": 6.213237762451172, "genuineness": 3.9550557136535645, "identity": 0.5339006781578064, "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/vn_VOLT_reg_high/c0f34e4767b330820a486ab72440fd19aa00cddd34d5d9e4f058de7ad2ba4ede.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": "c103cce6fe70e0ad9ffff4f0aded5ca67f8b0c4a125ffeaf8276047d441aa6bf", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "ef4c1b6810f0d2886c414618f8fc048d87338e78a2bdba9e5d1e88babc4903b1", "generation_seconds_batch": 16.25374490604736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.073773145675659, "target_z": -0.7031249281500083, "ce": 6.372091293334961, "genuineness": 4.6956281661987305, "identity": 0.5088465213775635, "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": 0.120000000000001, "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/vn_VOLT_reg_high/c103cce6fe70e0ad9ffff4f0aded5ca67f8b0c4a125ffeaf8276047d441aa6bf.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": "c13e1aa8dc3b59ea19367ef493ea899879ad8b8c834902c0dacb6bfbfa70eb95", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "5ee927278ede19ac1da7a68179c2b7ff9c4dd3a341dddaa7dfa6c1586e0d0ec8", "generation_seconds_batch": 14.714405186939985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.917722225189209, "target_z": -0.8828125348526079, "ce": 6.022613525390625, "genuineness": 4.557555198669434, "identity": 0.7226349115371704, "hypothesis": "Quelqu'un déplaçait 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/vn_VOLT_reg_high/c13e1aa8dc3b59ea19367ef493ea899879ad8b8c834902c0dacb6bfbfa70eb95.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": "c15db84656554f644eb8f5bd8e141375915708048309e2c344fde3303043e51c", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "3adc048e7ea3e9dd507d565bded27c6fc750d647b5ee59fd67674481ce5cfadb", "generation_seconds_batch": 15.706233208067715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3553431034088135, "target_z": -0.3789061945039243, "ce": 6.173524379730225, "genuineness": 4.193545341491699, "identity": 0.49221566319465637, "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/vn_VOLT_reg_high/c15db84656554f644eb8f5bd8e141375915708048309e2c344fde3303043e51c.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "c191f8bceb2eeac63603b39f3de2ee2d5a1dd640f0a172ed45493b419a781255", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "aa543bb6c9837d429bbda3bdc9412fab22de5a015a2dd90c3bf7957d80263bcb", "generation_seconds_batch": 15.056643356918357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6802536249160767, "target_z": -1.1562499764074654, "ce": 6.157639026641846, "genuineness": 3.9173994064331055, "identity": 0.3518999218940735, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c191f8bceb2eeac63603b39f3de2ee2d5a1dd640f0a172ed45493b419a781255.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "c1f4cae82be038e2e13357b6b7b7112cc8eb2c93fa6e54517b9ab2f121f30eea", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4e314270b6a2bb05bfdcac98f01b59307f172dde2636bffae452cc7e050947d5", "generation_seconds_batch": 20.61471846397035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2705328464508057, "target_z": -0.4765624726541076, "ce": 6.23706579208374, "genuineness": 4.2249250411987305, "identity": 0.661523163318634, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c1f4cae82be038e2e13357b6b7b7112cc8eb2c93fa6e54517b9ab2f121f30eea.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "c2491683397a2827829b3c2633f55ef8dc489b433dee709dfa3ae72db17e3ce9", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7688a4bc69de7f0ce634d2019dba2afbb956fae4cfc5a36631b3e3060f3fad95", "generation_seconds_batch": 21.37348916591145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5716965198516846, "target_z": -1.2812499849865688, "ce": 6.141753673553467, "genuineness": 4.030367851257324, "identity": 0.4144030213356018, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c2491683397a2827829b3c2633f55ef8dc489b433dee709dfa3ae72db17e3ce9.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": "c2dff8cb2da943449fd44f4767effe407c994745201734bdc4a68ce1090a7a5c", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d4566289e956395d0abac5d3531c383526e8eaa7ec11078256ce3f87d8d54130", "generation_seconds_batch": 21.537026252946816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1050655841827393, "target_z": 0.48437508471864693, "ce": 5.609594821929932, "genuineness": 3.5063188076019287, "identity": 0.21920821070671082, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houtenhek. Ik wacht aan de andere kant.", "wer": 0.14285714285714285, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c2dff8cb2da943449fd44f4767effe407c994745201734bdc4a68ce1090a7a5c.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "8c78f33a24fa1cd8f391209afb0889313bc154274e152e6c1ec1b9ca59c2f98e", "generation_seconds_batch": 15.827121507027186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.632759928703308, "target_z": -1.2109374372653057, "ce": 6.149696350097656, "genuineness": 4.300237655639648, "identity": 0.7651658654212952, "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/vn_VOLT_reg_high/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "c3c765f4fc299a8f0d5555182c8c89b3af888dbccbce76cdbc97ec6071896031", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0240147210bb37f3b41038890d3a2d7fce78cc56663351ffb89046f5ee690432", "generation_seconds_batch": 15.802890754071996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2586593627929688, "target_z": -0.4902344065013956, "ce": 5.990842819213867, "genuineness": 4.042920112609863, "identity": 0.5389677286148071, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c3c765f4fc299a8f0d5555182c8c89b3af888dbccbce76cdbc97ec6071896031.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "c4200c50ad71d1918d058375c00137eea62eabfaa38be36559b2f1723aae1b30", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc4cb562c4d9082fe631e8d29a98482aab35ac42b5213ff2e760b0bda2767fd3", "generation_seconds_batch": 21.066096176975407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.579241991043091, "target_z": -0.12109383981248963, "ce": 5.371314525604248, "genuineness": 3.8295347690582275, "identity": 0.42228689789772034, "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/vn_VOLT_reg_high/c4200c50ad71d1918d058375c00137eea62eabfaa38be36559b2f1723aae1b30.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "c44bf3a948a98325047dce983bf6653ed914ff408fb583adbe9cd36ea5d17bda", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "46ff7cfbb01b86b1dcf85b91527825772e38bd56bd1f74428c7e750ef41f5525", "generation_seconds_batch": 20.655509580974467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5174179077148438, "target_z": -1.3437500579089485, "ce": 5.816103935241699, "genuineness": 4.137060642242432, "identity": 0.6130152940750122, "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/vn_VOLT_reg_high/c44bf3a948a98325047dce983bf6653ed914ff408fb583adbe9cd36ea5d17bda.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "c454a8f4d03e7f547174568a4d1addc3d68a6fcc46c2254d6799b0318f0cb047", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "de988b415f4b2f0974697d1e6e151bc91c61a6a836ab599a5e5233f5bf4f81ed", "generation_seconds_batch": 22.1763423710363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6666839122772217, "target_z": -1.1718750632708883, "ce": 5.4944257736206055, "genuineness": 3.613011360168457, "identity": 0.4943360686302185, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c454a8f4d03e7f547174568a4d1addc3d68a6fcc46c2254d6799b0318f0cb047.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "556c341702d156c511e27d981c990450a20f5a399b305b276fdd66cd297be3ca", "generation_seconds_batch": 15.723141894908622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8023803234100342, "target_z": -1.0156250182305948, "ce": 6.141753673553467, "genuineness": 4.337893962860107, "identity": 0.7511929273605347, "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/vn_VOLT_reg_high/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "c4a2f53973ea0fc54f4c31f6f52072014f2b7209433f44e7e7b0452d690fa473", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "21cdbf653eae2baaf8bf071904bb50961494c6781518e7d5cc29fd2aa083af79", "generation_seconds_batch": 16.46181519597303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3681519031524658, "target_z": -1.5156250525470087, "ce": 6.260893821716309, "genuineness": 3.7918784618377686, "identity": 0.28850042819976807, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c4a2f53973ea0fc54f4c31f6f52072014f2b7209433f44e7e7b0452d690fa473.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "c4d8a4d55a576491705539c76ca88eb6b612729d66b53f807f342f4bb7537425", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4363780334a76d07e9cdf1f95cfb0fdca84c82b08b2549a1cbbd042330fa6a61", "generation_seconds_batch": 21.224263992044143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2552669048309326, "target_z": -0.49414071253366526, "ce": 5.736677646636963, "genuineness": 4.080576419830322, "identity": 0.568084716796875, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c4d8a4d55a576491705539c76ca88eb6b612729d66b53f807f342f4bb7537425.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "c508bc50942ac43e22db33e3d603be889a9d280001f7bae52d1f8768c5a4f120", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "16688afb3c494b3a400b782440ad62910f9da83586291abc3673108a6591e179", "generation_seconds_batch": 21.748338041943498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1484060287475586, "target_z": -0.6171875680966339, "ce": 6.022613525390625, "genuineness": 4.193545341491699, "identity": 0.4758264720439911, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c508bc50942ac43e22db33e3d603be889a9d280001f7bae52d1f8768c5a4f120.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "c51d572019aa8b24b3e18af0d1c924ccf450563e3ed81b1a23967ef9ea26da13", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6d8fa2cc6f0eb5b79b5d734919811957c40f0036b283a71d4b4151bcc3e928a8", "generation_seconds_batch": 21.72193162399344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.711545944213867, "target_z": 0.031249899195534035, "ce": 6.054384231567383, "genuineness": 4.005263805389404, "identity": 0.6503189206123352, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c51d572019aa8b24b3e18af0d1c924ccf450563e3ed81b1a23967ef9ea26da13.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "c521b75378ff3c4226e2b446c34193916ecee4ec3f1fcfdc586b5954e1141089", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d1fc58736bab146a06f9959caa3aca2dcf0300cb2ca6770886aee2352394771c", "generation_seconds_batch": 20.72035631502513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6666839122772217, "target_z": -1.1718750632708883, "ce": 6.300607204437256, "genuineness": 4.243753433227539, "identity": 0.437552809715271, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c521b75378ff3c4226e2b446c34193916ecee4ec3f1fcfdc586b5954e1141089.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "c531a1f219201316ae0468e741cdbe837007c3a439a4145347cec2f770fc2449", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "708701aa6f74f77b80d5ed4ec41fd627f5523f474036d24869672aada4ba87d0", "generation_seconds_batch": 15.382348119048402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6870384216308594, "target_z": -1.148437501608582, "ce": 6.260893821716309, "genuineness": 4.218649387359619, "identity": 0.17341165244579315, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c531a1f219201316ae0468e741cdbe837007c3a439a4145347cec2f770fc2449.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "c5bab344689e147ae733669a73406ea2b7aa85bb11ee7db69d9f7d509089b8a0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99e22d7d8c809d9c7677515c2892e91b35de59650bf79e9604dfc9bb66961a1b", "generation_seconds_batch": 22.069488772074692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8973677158355713, "target_z": -0.9062500965149142, "ce": 6.348263263702393, "genuineness": 4.457139015197754, "identity": 0.63261479139328, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c5bab344689e147ae733669a73406ea2b7aa85bb11ee7db69d9f7d509089b8a0.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "c5e57833632afd8bf56cf5e63e63e64dc0d5682d7414174ece61d49e1c0d0d90", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3efe81cee10540e34870cd6101eb23b2e73682887041667fb9f2f194d798f138", "generation_seconds_batch": 22.342707116971724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.734532117843628, "target_z": -1.0937500407507417, "ce": 6.197352409362793, "genuineness": 4.21237325668335, "identity": 0.439821720123291, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c5e57833632afd8bf56cf5e63e63e64dc0d5682d7414174ece61d49e1c0d0d90.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "c62219fa5be5a62f86114705932cb6af1d82fb8300c91070c7633d451b5b8be7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "021fc9bc16e9702b6ca4d8eb8948a662698d4a61a5dfab8c209cf3b1d699a756", "generation_seconds_batch": 22.22014442004729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9041526317596436, "target_z": -0.898437484450375, "ce": 6.260893821716309, "genuineness": 4.281409740447998, "identity": 0.3720044791698456, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c62219fa5be5a62f86114705932cb6af1d82fb8300c91070c7633d451b5b8be7.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "c67957e5fe3574f98ca6eb2f08669341aab4b04f5d50b36c5ef29163de88e015", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ca65ae0a5920afe73056cc30b71196773d503b09eecbc78a25a94a5242cdbbda", "generation_seconds_batch": 21.303853031946346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0873427391052246, "target_z": -0.6874999785522413, "ce": 6.062326908111572, "genuineness": 4.105680465698242, "identity": 0.7043744325637817, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c67957e5fe3574f98ca6eb2f08669341aab4b04f5d50b36c5ef29163de88e015.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "c67eda67c22b07419165b62d62ee13e3e974fc8ae2e77a52b9df48db10c21ad1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d9ccfe8fa3139fda516d1fc720d24f5a1e7d9725dbcfd934c8962962054e2f0c", "generation_seconds_batch": 20.614354143035598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5920509099960327, "target_z": -1.2578125605899184, "ce": 6.3641486167907715, "genuineness": 4.13078498840332, "identity": 0.47441309690475464, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschreiben.", "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/vn_VOLT_reg_high/c67eda67c22b07419165b62d62ee13e3e974fc8ae2e77a52b9df48db10c21ad1.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "c6abe818cf636aab3182835ebec9bd27cf5bb73d82b55b1707c4a6069f15a749", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0e19ab97a3dafedb75b4ce7303287d1c0bbe2605962c1a4b85f82937d8306389", "generation_seconds_batch": 22.1763423710363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0873427391052246, "target_z": -0.6874999785522413, "ce": 5.927301406860352, "genuineness": 4.2751336097717285, "identity": 0.6643968224525452, "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/vn_VOLT_reg_high/c6abe818cf636aab3182835ebec9bd27cf5bb73d82b55b1707c4a6069f15a749.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "c6ce49ec3a8b35b3928e64de8169d4061fccf6189b1caad619e66d9fd2e2518f", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6a0d3849ab4eb1354ad30a6417cc21a8f2593e78209de6f12b4283060bd7b872", "generation_seconds_batch": 15.576814447063953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3681519031524658, "target_z": -1.5156250525470087, "ce": 6.340320587158203, "genuineness": 3.911123275756836, "identity": 0.4175211191177368, "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/vn_VOLT_reg_high/c6ce49ec3a8b35b3928e64de8169d4061fccf6189b1caad619e66d9fd2e2518f.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "c6f6145b5c79212dd3556f8859ccf9bdc8d3c569dda16a72aebec0150d5b0d3b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ae04606511c04d903af4cd82dcfa085126d74fd9d6c8899838b7eceb7a2caa93", "generation_seconds_batch": 15.698437181999907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5581269264221191, "target_z": -1.296874934584336, "ce": 6.157639026641846, "genuineness": 3.9550557136535645, "identity": 0.4673578143119812, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c6f6145b5c79212dd3556f8859ccf9bdc8d3c569dda16a72aebec0150d5b0d3b.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": "c795df177a6ef830228de8fd61ff233e6fd2b71539316985ae8f4091ff10a62c", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f88b8b53f11a74e5bf38798fe0ff0c2a454292ddef9aa04d4149acaea4d8aa7", "generation_seconds_batch": 22.030410493025556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9686083793640137, "target_z": -0.8242187679624979, "ce": 5.879645347595215, "genuineness": 4.268857479095459, "identity": 0.7892446517944336, "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/vn_VOLT_reg_high/c795df177a6ef830228de8fd61ff233e6fd2b71539316985ae8f4091ff10a62c.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "c7b8e03d8cadacbd899423b8245a61910cfbd3a859f99acd7138c5bd044a806d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "148068ea2e2b8c5fb5a561397f7fc01f12bf48a39976f4cb2f1c3e87ab31db05", "generation_seconds_batch": 22.234715519007295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.2767791748046875, "genuineness": 4.607763767242432, "identity": 0.6524080038070679, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c7b8e03d8cadacbd899423b8245a61910cfbd3a859f99acd7138c5bd044a806d.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "09f5a01260daa36e5a5072dec3ec0359a75d5f66dc37d5c1696ea2430f4b4c45", "generation_seconds_batch": 16.560262896004133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1517984867095947, "target_z": -0.6132812620643643, "ce": 6.117925643920898, "genuineness": 4.21237325668335, "identity": 0.6175062656402588, "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/vn_VOLT_reg_high/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "c8224e29a777cfec611d34fccbf3a432e9a1efe92840d681e1dd52427c0dd0da", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "66b145b8fa1f24c9fc1d4e5ce6c7608a35dcabbebabf85b831bcef99941d55c7", "generation_seconds_batch": 15.924648014013655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7209625244140625, "target_z": -1.1093749903485086, "ce": 6.117925643920898, "genuineness": 4.319066047668457, "identity": 0.3327426016330719, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c8224e29a777cfec611d34fccbf3a432e9a1efe92840d681e1dd52427c0dd0da.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "c86c1ae4e11e465d7c7e0342b70da4ffafe68bd3776e92d1798074c873221253", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e6c995d1d694305b01cd7fbc682ca55f050083bc9eb4d6b00bb70e0e6353167d", "generation_seconds_batch": 14.803139630006626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.266379714012146, "target_z": -1.632812449061573, "ce": 6.181467056274414, "genuineness": 3.9550557136535645, "identity": 0.31460750102996826, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c86c1ae4e11e465d7c7e0342b70da4ffafe68bd3776e92d1798074c873221253.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "dee54aa9df5a0f9a7eaec7710561a13c74097dc4e16ee4d940c445ae4b25797a", "generation_seconds_batch": 15.457568651996553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.324435234069824, "genuineness": 4.356721878051758, "identity": 0.40773579478263855, "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/vn_VOLT_reg_high/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "c89451931f917fa86eeb4009b925249cba634acc276835d2dc6d774a470f38a5", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4ca2bac8743ee52f83836b1247e96cec1a056da94e6a66f31d77edc64ffd7324", "generation_seconds_batch": 21.756857234053314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3817216157913208, "target_z": -1.499999965683586, "ce": 6.316492557525635, "genuineness": 4.444586753845215, "identity": 0.3014482855796814, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c89451931f917fa86eeb4009b925249cba634acc276835d2dc6d774a470f38a5.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "c8a14b2f1bfea5f2cf7efb73735ac3c60af648f352c8c3e33336cce8800c238b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8d4b9a8654ed921c2186f66a27efbae4aa65628f7011bdacbf513d4b0253c733", "generation_seconds_batch": 21.436250232043676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8634437322616577, "target_z": -0.9453124705093318, "ce": 6.332377910614014, "genuineness": 4.281409740447998, "identity": 0.29074668884277344, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c8a14b2f1bfea5f2cf7efb73735ac3c60af648f352c8c3e33336cce8800c238b.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "c90137449ef8b25795e9791da6e697f65613de19deccec19a8b9e690b2635fbd", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3f93cf95ddf3f38640455b90f5d12d2a9e877bd8bdc55810331747a61eec031e", "generation_seconds_batch": 21.297413734020665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8794703483581543, "target_z": 0.22460943974542164, "ce": 6.0146708488464355, "genuineness": 3.760498285293579, "identity": 0.36365267634391785, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c90137449ef8b25795e9791da6e697f65613de19deccec19a8b9e690b2635fbd.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "c97f4e28db9c2630006f93b3d8ff4f86cde18582ab4d52355f0939a07c377262", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "be7469ead325335a533d6f55ad74707d99e19994a7106025e5c908ece9fa8a0c", "generation_seconds_batch": 22.015541894943453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4985849857330322, "target_z": 0.9374999957104483, "ce": 5.784333229064941, "genuineness": 4.068024158477783, "identity": 0.547496497631073, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c97f4e28db9c2630006f93b3d8ff4f86cde18582ab4d52355f0939a07c377262.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "c9cdaff5327dfff0c989532644c8245fa54385fee40bf293172e7a001a90c80f", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0cc6bec0cc4d6aa45aceb6617a1ece80883ef5037d869137376638f337a5ccac", "generation_seconds_batch": 15.590250822948292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3681519031524658, "target_z": -1.5156250525470087, "ce": 6.427689552307129, "genuineness": 4.143336772918701, "identity": 0.5193076133728027, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c9cdaff5327dfff0c989532644c8245fa54385fee40bf293172e7a001a90c80f.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "c9e70ff57b4bf7b49602cf96d4321dd0e7f6d748fe367bc000727b18e605efec", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "15ab6021d702137e3030f89b7459df307f7c194c7b146b18a19316c3ab8443e1", "generation_seconds_batch": 16.334690026007593, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4563546180725098, "target_z": -1.414062468364556, "ce": 6.324435234069824, "genuineness": 4.68307638168335, "identity": 0.7343522906303406, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/c9e70ff57b4bf7b49602cf96d4321dd0e7f6d748fe367bc000727b18e605efec.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "ca16b0a1d3c22ff56182155cc62cfeddf872799da95e04df5ec23baf4bee5d87", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fb1a9001b688c4c6ec4d40d1d2bccac62079f068ccd81122f7e534f5aa7d5a5b", "generation_seconds_batch": 15.255104401963763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7277473211288452, "target_z": -1.1015625155496251, "ce": 6.181467056274414, "genuineness": 4.570107460021973, "identity": 0.6350840926170349, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ca16b0a1d3c22ff56182155cc62cfeddf872799da95e04df5ec23baf4bee5d87.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "ca8a16234f906577f89751267cf28f266ef11657839928d3209756f1feeeaed1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "408ad217ef116de5df260b8b18449152064534649b5eb1189e5c22af030ab8f7", "generation_seconds_batch": 21.406064387992956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.043241500854492, "target_z": -0.738281133377812, "ce": 6.205295085906982, "genuineness": 4.325342178344727, "identity": 0.7476956844329834, "hypothesis": "Ik 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/vn_VOLT_reg_high/ca8a16234f906577f89751267cf28f266ef11657839928d3209756f1feeeaed1.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "cabfa220e2d883f76ad0698b1b31696cc130d544cd8bfba267ed184c301dabd0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d7f4adb6a3fe5eac2d1acb834fa0e3272830e8b3aebf9e08e25e92b28a030fb9", "generation_seconds_batch": 14.860142746008933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7006080150604248, "target_z": -1.132812552010815, "ce": 6.356205940246582, "genuineness": 4.494794845581055, "identity": 0.4544493556022644, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cabfa220e2d883f76ad0698b1b31696cc130d544cd8bfba267ed184c301dabd0.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "cac6db2a594243ead74c21b2ec25e89c5765bd440f7eb2c2918a81e1b881844e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fe781a6fea279505477552a66da4f43cd5adeb38041882b9f5dc577a73dce222", "generation_seconds_batch": 21.432823205017485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.005924940109253, "target_z": -0.7812499506701549, "ce": 6.205295085906982, "genuineness": 4.457139015197754, "identity": 0.5480109453201294, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cac6db2a594243ead74c21b2ec25e89c5765bd440f7eb2c2918a81e1b881844e.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "cac9ec2a806ecebd1367fd1eb20cdc0bee4cfda0a9046a990ac6f4a60c41c72d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "72663710ea0b3a09b1ca06f67c43e5289d13f9683a023b198b6b25a676481d23", "generation_seconds_batch": 21.424265785957687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5716965198516846, "target_z": -1.2812499849865688, "ce": 6.348263263702393, "genuineness": 4.193545341491699, "identity": 0.6265561580657959, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cac9ec2a806ecebd1367fd1eb20cdc0bee4cfda0a9046a990ac6f4a60c41c72d.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "cad07848a6317b65cd6aeafd9513800c6b79ceef4541a36ff38078f78b8439c0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e3f4a916ab9c55ac8ce695d64bed82ccc8b4d47d97dd0f57ab393fbd33412d1b", "generation_seconds_batch": 20.640219485969283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7955955266952515, "target_z": -1.0234374930294785, "ce": 6.054384231567383, "genuineness": 4.243753433227539, "identity": 0.6647341251373291, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cad07848a6317b65cd6aeafd9513800c6b79ceef4541a36ff38078f78b8439c0.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "caed93849b0853acee38a0f06aa149ae6a7b0e6a3345dadae71f64499fd07102", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ebf879fa02535dac925f03afdfcb1ff8d7e02108e5fd9162041448fae9af7c76", "generation_seconds_batch": 15.907162116025575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.32744300365448, "target_z": -1.5625000386059658, "ce": 6.41180419921875, "genuineness": 4.381826400756836, "identity": 0.4551560580730438, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/caed93849b0853acee38a0f06aa149ae6a7b0e6a3345dadae71f64499fd07102.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": "cb357a80fd043d6fa6a4dc4b77d172dbe9393d913c40abe1a071434a89ebfbdb", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Your message arrived after I had left.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "23a96361e2fd131130c68ff0af1d58205180b62300aa60cfb110f679f91fd877", "generation_seconds_batch": 22.188285840908065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6598117351531982, "target_z": -0.028320375569815474, "ce": 6.221180438995361, "genuineness": 3.7793264389038086, "identity": 0.3149260878562927, "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/vn_VOLT_reg_high/cb357a80fd043d6fa6a4dc4b77d172dbe9393d913c40abe1a071434a89ebfbdb.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "cb497aed4637e1d51e455ca5bbd6a280294c251747849baf1dff0ad2b3c6f239", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a297de9dabe5d59a30949854fa1d7592c7e2aea5e05dc933c76138e1497601f2", "generation_seconds_batch": 17.35800002096221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9312918186187744, "target_z": -0.8671875852548409, "ce": 5.772419452667236, "genuineness": 4.250029563903809, "identity": 0.6435540914535522, "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/vn_VOLT_reg_high/cb497aed4637e1d51e455ca5bbd6a280294c251747849baf1dff0ad2b3c6f239.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "cb523006f5579cf9ccc121b0f18d74ca19180feb55a1578e4e6a61454bcc344e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "90b1c79dbca1d4ea8a1ea14c2f2d67c2a867b74949ed4b3eaa9231357e41bb44", "generation_seconds_batch": 14.476241000927985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4292153120040894, "target_z": -1.4453125048257458, "ce": 6.078212261199951, "genuineness": 4.118232727050781, "identity": 0.5070298910140991, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cb523006f5579cf9ccc121b0f18d74ca19180feb55a1578e4e6a61454bcc344e.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "cba8f8b0dfc481123af3d76674a8b29aae9a38ac700a07671485ee94d699eb77", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "41fd24cea9ef52bf0c69573bce366343fb81b05c2718cba93812a1238198270b", "generation_seconds_batch": 21.88208942406345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.415645718574524, "target_z": -1.4609374544235127, "ce": 5.919358730316162, "genuineness": 4.218649387359619, "identity": 0.6468993425369263, "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/vn_VOLT_reg_high/cba8f8b0dfc481123af3d76674a8b29aae9a38ac700a07671485ee94d699eb77.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "cc23a2a27120d0c9bf6cec0f0aa620b5f4b34a1ce4005c7d8edb38488dcee6e3", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "254d7160304179369c8073c129234627f04a1281b806d082e17a93b158fc09d2", "generation_seconds_batch": 16.290545369964093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.436000108718872, "target_z": -1.437500030026862, "ce": 6.205295085906982, "genuineness": 4.293961524963379, "identity": 0.3591468930244446, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cc23a2a27120d0c9bf6cec0f0aa620b5f4b34a1ce4005c7d8edb38488dcee6e3.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "ccbceb450de2262ce60d3ae6e6d03759ba2ea2767cbe800edd0295148bdc71ee", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d8ae524a5a42298a3ecb2d527109aacae2a93e56f2ffdde1a3640e7d7d197ef8", "generation_seconds_batch": 21.88644194090739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.563976287841797, "target_z": -0.13867180516073568, "ce": 5.8875885009765625, "genuineness": 4.005263805389404, "identity": 0.4332088828086853, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ccbceb450de2262ce60d3ae6e6d03759ba2ea2767cbe800edd0295148bdc71ee.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "ccc5b81e0b5a7544eaabab36cbed3302b3ec0f4e1bc852f7690677d8c0e8ffb6", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ddfe01a6a5723d2359de7eaf8ecbca59b78d2a3a5b42d9bf5cdb619e55fe9ea6", "generation_seconds_batch": 21.407817402970977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4079253673553467, "target_z": -0.3183594118633353, "ce": 6.308549880981445, "genuineness": 4.124508857727051, "identity": 0.5148988962173462, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ccc5b81e0b5a7544eaabab36cbed3302b3ec0f4e1bc852f7690677d8c0e8ffb6.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "cd0d0c8a5584c42e4b6283d84f7c525ed71194705bba715a6bc86f4f537eb76a", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e655cac5aaa41559f0fd1a7b4a4b31843868810165d71e3ae1c6359c7169f4ba", "generation_seconds_batch": 15.590250822948292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.266379714012146, "target_z": -1.632812449061573, "ce": 6.213237762451172, "genuineness": 4.118232727050781, "identity": 0.49414438009262085, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cd0d0c8a5584c42e4b6283d84f7c525ed71194705bba715a6bc86f4f537eb76a.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "cd576ef66a3f9017917d5303b79992f5c9af65d28c1af56e93179a1b7ceb552e", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a6e15662c6a86607aea89bfe2842affe453781cbd568bff75cbb5024e2102148", "generation_seconds_batch": 16.018694182974286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.086154937744141, "genuineness": 4.3881025314331055, "identity": 0.7190966606140137, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cd576ef66a3f9017917d5303b79992f5c9af65d28c1af56e93179a1b7ceb552e.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": "cdc1b39efc3ed1522faebbd69bded45ce28c6e4947cb06343ffe80e38b9e027e", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "27a605662d1d210405b47bcaec0602d7edb16ddf5cd96f393b2ae313864ff462", "generation_seconds_batch": 15.812409925973043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2026846408843994, "target_z": -0.5546874951742543, "ce": 5.839932441711426, "genuineness": 4.231201171875, "identity": 0.5739914178848267, "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/vn_VOLT_reg_high/cdc1b39efc3ed1522faebbd69bded45ce28c6e4947cb06343ffe80e38b9e027e.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "ce27979f79d541a74835c4ae522d7cc3620f8ee67f9ab30eaf6e223d255e9c44", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "708a92c8ecb66c0f71eadcdfce069f1e1dae7b5da5a29ffbe8d712543246c9af", "generation_seconds_batch": 16.587533309939317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3003038167953491, "target_z": -1.5937499378014996, "ce": 6.395919322967529, "genuineness": 4.168440818786621, "identity": 0.5641994476318359, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ce27979f79d541a74835c4ae522d7cc3620f8ee67f9ab30eaf6e223d255e9c44.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": "ce4ec225bfc59aaf218f9cef2a34e9053eb1f2eb9440671c2ef016fcc2316111", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "8b0be2428f4d374f80cf8a043f46b46d73ae94a751b6077a5cc3ec6a9e2bde2d", "generation_seconds_batch": 14.997609446989372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8794703483581543, "target_z": 0.22460943974542164, "ce": 6.0305562019348145, "genuineness": 4.20609712600708, "identity": 0.5933641195297241, "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/vn_VOLT_reg_high/ce4ec225bfc59aaf218f9cef2a34e9053eb1f2eb9440671c2ef016fcc2316111.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "ce6c94ccd92ecfb06fc918389af66e555f188cdf2a8a809ecec0c6761a127d6d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d47316159d7743ab7b9d7b9df1ad85609ba7a8dfd8e80ab4b1ed5e692e2f99a7", "generation_seconds_batch": 21.289375439984724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.152559280395508, "target_z": 0.5390625455764873, "ce": 6.046441555023193, "genuineness": 3.835810661315918, "identity": 0.5799052715301514, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ce6c94ccd92ecfb06fc918389af66e555f188cdf2a8a809ecec0c6761a127d6d.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "ce7a65f7c5d8d3dfa679d47730841d2a2c41f66427dece8634c51f19dea15c00", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "15a122d6294d444308e922f2c715212df11cbe35a4b89d3732230913812e00ed", "generation_seconds_batch": 15.539590282016434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.655571222305298, "target_z": -0.03320318947732464, "ce": 5.967014789581299, "genuineness": 4.218649387359619, "identity": 0.5634675025939941, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ce7a65f7c5d8d3dfa679d47730841d2a2c41f66427dece8634c51f19dea15c00.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "cf4a88d37301e635cd9f793c08ad5ac559cdb8eaff794c880984074b15e0a2cf", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8b6bcbe7b22913179ef8b9bc4403d4e21b1d128a740888644d5a96ffac74f7c0", "generation_seconds_batch": 20.44068189896643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479166030883789, "target_z": -0.236328083310919, "ce": 5.796247482299805, "genuineness": 3.8671910762786865, "identity": 0.3965415954589844, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cf4a88d37301e635cd9f793c08ad5ac559cdb8eaff794c880984074b15e0a2cf.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "51d0b199db18516063a0c190e097faae1c36d10b6cdc623a768b50d804066bf0", "generation_seconds_batch": 14.91730610805098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7413170337677002, "target_z": -1.0859374286862022, "ce": 6.38797664642334, "genuineness": 4.356721878051758, "identity": 0.5652817487716675, "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/vn_VOLT_reg_high/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "cf852bc167fa644eecfa6321e7998737fdf7c6bf05a497b175262fcc00f1ea12", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "295ef4113b3cef2c6f361473de18a4d7e73eb1b5eeae1d83a098c9196dd8ed59", "generation_seconds_batch": 21.424265785957687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8634437322616577, "target_z": -0.9453124705093318, "ce": 6.308549880981445, "genuineness": 4.582659721374512, "identity": 0.6645922660827637, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cf852bc167fa644eecfa6321e7998737fdf7c6bf05a497b175262fcc00f1ea12.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": "cf860b716266497af5174acd03799c75de98e0eda2bcb91fa7075fcac0a40c2c", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da14c69748b988eb6bfff50f876914299a94b4d71e9aa46628408b302e2d723d", "generation_seconds_batch": 21.843643672997132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8133182525634766, "target_z": 0.148437432975754, "ce": 6.0146708488464355, "genuineness": 3.9299514293670654, "identity": 0.5782572627067566, "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/vn_VOLT_reg_high/cf860b716266497af5174acd03799c75de98e0eda2bcb91fa7075fcac0a40c2c.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "cfa1767ed47d929e40f764721a3771214041dc16e5102cc1367876d705b200ba", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "55633d32258cfb6013891e3be4741996c781f27f63231f584a9cb22bc16340a8", "generation_seconds_batch": 15.235562562011182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6802536249160767, "target_z": -1.1562499764074654, "ce": 6.0146708488464355, "genuineness": 4.3881025314331055, "identity": 0.6143361926078796, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cfa1767ed47d929e40f764721a3771214041dc16e5102cc1367876d705b200ba.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "cff4f0ea56146b56948abd89850bb28c050f3f02e5e36c0ac4327e8ff4644bf4", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d1c9d4469b44f2baa2396aa805f1deb1a63d088b11d2fcf656eb27a94e99386", "generation_seconds_batch": 16.551221503061242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0873427391052246, "target_z": -0.6874999785522413, "ce": 6.0305562019348145, "genuineness": 4.143336772918701, "identity": 0.37331971526145935, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/cff4f0ea56146b56948abd89850bb28c050f3f02e5e36c0ac4327e8ff4644bf4.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "d010ce6cf0bd6d05fc6c4011a3fcffd292dfd503bc820879267b91acdbbd8cd2", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bd2890146477c5a8aa72914da02a252957c96494928b579abf960c41e4299044", "generation_seconds_batch": 15.242842889972962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8023803234100342, "target_z": -1.0156250182305948, "ce": 6.125868320465088, "genuineness": 4.21237325668335, "identity": 0.5276200175285339, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d010ce6cf0bd6d05fc6c4011a3fcffd292dfd503bc820879267b91acdbbd8cd2.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "d03dce7448fd4e07821e7f9d3f76a33bd6dcb1905fcd0beac28dee07ce0eef17", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc4963fc44f394e6dc5a876659248a2b15021c05e85290dc7160945381db54c1", "generation_seconds_batch": 15.257347498089075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5716965198516846, "target_z": -1.2812499849865688, "ce": 6.260893821716309, "genuineness": 4.582659721374512, "identity": 0.7295454740524292, "hypothesis": "La porte 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/vn_VOLT_reg_high/d03dce7448fd4e07821e7f9d3f76a33bd6dcb1905fcd0beac28dee07ce0eef17.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": "d117b7784dd86f86d9c511a984ace722a26e6ca576e7624fcdf93a9689560bb9", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "676cf9aa92f6095b060943b1dac28e137aacb506a250fdf8e21ffb42c92f1aac", "generation_seconds_batch": 15.360149635002017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6531143188476562, "target_z": -1.1875000128686553, "ce": 6.419747352600098, "genuineness": 4.375550270080566, "identity": 0.3198002576828003, "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/vn_VOLT_reg_high/d117b7784dd86f86d9c511a984ace722a26e6ca576e7624fcdf93a9689560bb9.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "cfa0acbf7ce6464ea8a21ecd17463f02e7db597e5d4174ce8fe7f351991b4673", "generation_seconds_batch": 14.613188895047642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.693823218345642, "target_z": -1.1406250268096985, "ce": 6.348263263702393, "genuineness": 4.243753433227539, "identity": 0.21433353424072266, "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/vn_VOLT_reg_high/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "d184cffa3d69ab873ab6531817d0a20b0cb556cf7954c8e62f86dee7a7612fba", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c2e03e0ac89ded4cc3f523c8d3072d2cdfd369dc093e3ad013a6f321528af8dd", "generation_seconds_batch": 15.89797498495318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.32744300365448, "target_z": -1.5625000386059658, "ce": 6.443574905395508, "genuineness": 4.15588903427124, "identity": 0.5930461883544922, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d184cffa3d69ab873ab6531817d0a20b0cb556cf7954c8e62f86dee7a7612fba.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "d18872651ddad0db439d1748b6ac3b5dde4cd656620e43bfe34408e255e4c830", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b751593bc24f97a66e68d2bed70af9be2b31149cdd2e76375a99f9bc8e5498c7", "generation_seconds_batch": 15.034934246912599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3342278003692627, "target_z": -1.5546875638070823, "ce": 6.205295085906982, "genuineness": 4.432034492492676, "identity": 0.6139851808547974, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d18872651ddad0db439d1748b6ac3b5dde4cd656620e43bfe34408e255e4c830.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "d1d300b51e3e5d93f9c8e7bca8d78ddf0b51ad7f3717d7785c3b5efa73df1910", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "49a0e127627ace04b7bfd0e7ef0458be6b2988fcf6e9d5664bcaef4b77fe61cd", "generation_seconds_batch": 22.212902792030945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7413170337677002, "target_z": -1.0859374286862022, "ce": 6.117925643920898, "genuineness": 4.595211505889893, "identity": 0.7772070169448853, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la. près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d1d300b51e3e5d93f9c8e7bca8d78ddf0b51ad7f3717d7785c3b5efa73df1910.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": "d214ca03cbe91963767b0a6d23882a9cfd9b8a7c9ee73995bf886509fcdf84d8", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8763051e172b3518c788bf09c1d9d6d15933f95760e12793f828fbcb2f5422e7", "generation_seconds_batch": 14.130596464965492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.155951738357544, "target_z": 0.542968851608757, "ce": 5.903473377227783, "genuineness": 3.8169827461242676, "identity": 0.6088352203369141, "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/vn_VOLT_reg_high/d214ca03cbe91963767b0a6d23882a9cfd9b8a7c9ee73995bf886509fcdf84d8.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "adbc436e515339b584fa7ca9e54632a26fb93aead5ec1b5c9ffcc4ef5dfdecd0", "generation_seconds_batch": 15.145513245020993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5445572137832642, "target_z": -1.3125000214477587, "ce": 6.229123115539551, "genuineness": 4.306513786315918, "identity": 0.7643805742263794, "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/vn_VOLT_reg_high/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "d25640e1a0a11704d844c4eb97e58538c382537ab0e9339f2f7e5a667deb9bb0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a282bfc744b940306dbcc2855499f0220cc14c1c5534045b776f4f033a1cf953", "generation_seconds_batch": 20.792780348914675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.308609962463379, "target_z": 0.7187498777477753, "ce": 5.911416053771973, "genuineness": 4.036643981933594, "identity": 0.6363827586174011, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d25640e1a0a11704d844c4eb97e58538c382537ab0e9339f2f7e5a667deb9bb0.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "d2577e4c0d738e56ca98ae50edc3d4cf25b5f3f44c9c3fdc6b97a3fa99514917", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ecf9524365ae4cb87ff49171d5005e5ab6c279e0bed4b38ff6044f732710787d", "generation_seconds_batch": 16.16089773294516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8023803234100342, "target_z": -1.0156250182305948, "ce": 6.2767791748046875, "genuineness": 4.432034492492676, "identity": 0.2675018906593323, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d2577e4c0d738e56ca98ae50edc3d4cf25b5f3f44c9c3fdc6b97a3fa99514917.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "d2ab16d3b0cd05855a9093e53dabc600185593ce01ad4257e503a3df028e65ef", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "07bc986d22ca95150f1e4b5c5c219ff3db91bff3b204e7c4deb736b940390216", "generation_seconds_batch": 22.37711906689219, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8497867584228516, "target_z": 0.19042974239285745, "ce": 6.078212261199951, "genuineness": 3.7291181087493896, "identity": 0.47342872619628906, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d2ab16d3b0cd05855a9093e53dabc600185593ce01ad4257e503a3df028e65ef.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "d347e4611a3172b4edd2daed8ec2d5969d14edaabd2b52ec5d5de9a55bf3943c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3e3730ed471f2cd38b401f75dbba40e9470151b1efcfbaeec956d64056410476", "generation_seconds_batch": 15.450467288028449, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4292153120040894, "target_z": -1.4453125048257458, "ce": 5.816103935241699, "genuineness": 3.9801597595214844, "identity": 0.7057141661643982, "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/vn_VOLT_reg_high/d347e4611a3172b4edd2daed8ec2d5969d14edaabd2b52ec5d5de9a55bf3943c.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "d34a91a4e4252517ab5323e1c33ee21f42dc0ef9bbfc8141524ff33a4c0d6d25", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "78ae33c6973a151a0b07798e2acdbd0e988ba3753e86beb90e333c4189bd87ed", "generation_seconds_batch": 15.506394125986844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1280517578125, "target_z": -0.6406248552276287, "ce": 5.871703147888184, "genuineness": 4.15588903427124, "identity": 0.27952471375465393, "hypothesis": "De deur 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/vn_VOLT_reg_high/d34a91a4e4252517ab5323e1c33ee21f42dc0ef9bbfc8141524ff33a4c0d6d25.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "d365e05525acb244e402104bfdbc33b4ee5d8b282d97c930a807bf0365a79e82", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b4a61d31568b4aa2c9890d77196b7a6087b82012f7197605284a177c7ed9537d", "generation_seconds_batch": 21.528232307056896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.104304790496826, "target_z": -0.6679687229222047, "ce": 6.070269584655762, "genuineness": 4.042920112609863, "identity": 0.6720329523086548, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d365e05525acb244e402104bfdbc33b4ee5d8b282d97c930a807bf0365a79e82.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": "d38d32e68693efa68ebef5005a0a8f65883c64485fe1d2e69c8893d8e2f322dc", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The keys are on the kitchen table.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "c2422c264696fe65c4b1d3d0c1303797f2a52aca43534e4effb00e04b00f9d1a", "generation_seconds_batch": 15.577773706056178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.304456949234009, "target_z": -0.4374999613940343, "ce": 6.268836498260498, "genuineness": 4.15588903427124, "identity": 0.5111693143844604, "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/vn_VOLT_reg_high/d38d32e68693efa68ebef5005a0a8f65883c64485fe1d2e69c8893d8e2f322dc.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "d397b1060746a679f41b2921c297f6637fcb37d092b9fc8858730dfe340b2b6a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "690d99f6f365d17773d3abb13893883d2a3b02e22ce9ccb4c9bfb1a5fe9a9de9", "generation_seconds_batch": 20.926643955986947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4985849857330322, "target_z": 0.9374999957104483, "ce": 5.8875885009765625, "genuineness": 3.6914620399475098, "identity": 0.5587092638015747, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d397b1060746a679f41b2921c297f6637fcb37d092b9fc8858730dfe340b2b6a.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "5e144775161afc22707765192343820f4a63822c9a2808f15bb7c318c8e249d7", "generation_seconds_batch": 16.136823267908767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2935189008712769, "target_z": -1.601562549866039, "ce": 6.046441555023193, "genuineness": 4.319066047668457, "identity": 0.747909426689148, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et verifie 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/vn_VOLT_reg_high/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.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": "d40549e6fdcc6657e0a6f08f19a1eee6e90d64d98609ee8879a52bcb2c48ecda", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b936577242d0b28a14c33bdb61991fa039a4ca819eaf98933c350b70bc77a54", "generation_seconds_batch": 21.604011559975334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.798900604248047, "target_z": 0.13183597550274748, "ce": 6.133810997009277, "genuineness": 4.118232727050781, "identity": 0.30761802196502686, "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/vn_VOLT_reg_high/d40549e6fdcc6657e0a6f08f19a1eee6e90d64d98609ee8879a52bcb2c48ecda.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "d4628650d5eee767fcf1edb4208c7bc449dd41b5a66b15032fdd1d34686b6b5e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "bd888902026b802332c81ae387952b3bbbcc9d4267b86deca0de9930d250d6b5", "generation_seconds_batch": 19.649951436091214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6395447254180908, "target_z": -1.2031249624664222, "ce": 6.117925643920898, "genuineness": 4.293961524963379, "identity": 0.3113425672054291, "hypothesis": "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/vn_VOLT_reg_high/d4628650d5eee767fcf1edb4208c7bc449dd41b5a66b15032fdd1d34686b6b5e.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "d472715b65b22151fc297e342b91e816e0a8261879cc9802cae339ddc0ce1c6c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "01addb83a94b7a6057b43b031b4ae0f8f8dfcb38d2dc57b113df20e4e22c0fbd", "generation_seconds_batch": 21.717028753017075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.341773509979248, "target_z": -0.3945311441016913, "ce": 5.748591423034668, "genuineness": 4.011539936065674, "identity": 0.4791540801525116, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d472715b65b22151fc297e342b91e816e0a8261879cc9802cae339ddc0ce1c6c.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": "d477b26638daba64c2afe56b8641617cea310d94993293905dd4bad051de0298", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93416b3ab3bf35714eb1fb9712ba72bfbedf3de9d74be3674cf0005d35f5340b", "generation_seconds_batch": 14.078956342069432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348558187484741, "target_z": -0.38671880656846364, "ce": 6.078212261199951, "genuineness": 4.1998209953308105, "identity": 0.6770296096801758, "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/vn_VOLT_reg_high/d477b26638daba64c2afe56b8641617cea310d94993293905dd4bad051de0298.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "d4f6325de5f62a8d6b2f0a4a3da4e2e133b0cdec6ee00d91662c77d660ac4e04", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P04", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Think while speaking, with small organic hesitations and spontaneous emphasis.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "697a0b341dd996e9f341021f62cd240318510b31e4d24646e4fd104b546dc99d", "generation_seconds_batch": 15.11819118494168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.524202823638916, "target_z": -1.3359374458444093, "ce": 6.324435234069824, "genuineness": 4.469690799713135, "identity": 0.4835686683654785, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d4f6325de5f62a8d6b2f0a4a3da4e2e133b0cdec6ee00d91662c77d660ac4e04.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "d55bc2485c2fe5493db71818a0577b7382bd6edff781338d91d3488e57394aa5", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96d639167648d8d944d222ee9c121ca72d825536e7716bccf51439d332f8188c", "generation_seconds_batch": 19.859023174038157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3003038167953491, "target_z": -1.5937499378014996, "ce": 5.879645347595215, "genuineness": 3.8420867919921875, "identity": 0.4631134271621704, "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/vn_VOLT_reg_high/d55bc2485c2fe5493db71818a0577b7382bd6edff781338d91d3488e57394aa5.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "d5b2760ff099f5e6381919ac3d63b80324ca545cd04f1a79912048a00840da56", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "72038655bad47f28033537287f9ac27e63631aaed27e00949f71fb08cf01c585", "generation_seconds_batch": 21.12516679696273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.66235613822937, "target_z": -0.02539057741278535, "ce": 6.078212261199951, "genuineness": 3.886019229888916, "identity": 0.4918321371078491, "hypothesis": "Ik 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/vn_VOLT_reg_high/d5b2760ff099f5e6381919ac3d63b80324ca545cd04f1a79912048a00840da56.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "d5e1ec5aaddb473fa1b9b2e9e077359ce1a90d2dffe856467c17a11dcce7c5ac", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f048806b89b01700a8e9206dfd6e3777deb9581e2541c8135030716240868ea8", "generation_seconds_batch": 21.06881698104553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8464816808700562, "target_z": -0.9648437261393684, "ce": 6.086154937744141, "genuineness": 4.256305694580078, "identity": 0.4449438750743866, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d5e1ec5aaddb473fa1b9b2e9e077359ce1a90d2dffe856467c17a11dcce7c5ac.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "d5fb90bd3982e1282a44a79ae83a91c47a6cc87548a6cc23cfd4a09c7ca6a3e7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "641430095cf7cf37ffeb6a29667afd75fa3f96b694abc78d638bcc69890fbb13", "generation_seconds_batch": 20.011492097983137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3926596641540527, "target_z": -0.33593737721158135, "ce": 5.911416053771973, "genuineness": 3.8295347690582275, "identity": 0.7478195428848267, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d5fb90bd3982e1282a44a79ae83a91c47a6cc87548a6cc23cfd4a09c7ca6a3e7.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "d610aeed1c1f82069cd84d2e8e5a1bb3e80e6cad17e52a39cd9886323f3ddcb9", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "923e4909a733aed2c4a9f0cb8209f4284cab279da0f3141f714d60d09be41208", "generation_seconds_batch": 22.015541894943453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5504066944122314, "target_z": -0.15429675475850269, "ce": 6.0146708488464355, "genuineness": 3.9173994064331055, "identity": 0.5292034149169922, "hypothesis": "J'ai trouvé la petite boite. Elle était prêt de la vie fenêtre. We've regarded ensemble what contiene.", "wer": 0.47368421052631576, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d610aeed1c1f82069cd84d2e8e5a1bb3e80e6cad17e52a39cd9886323f3ddcb9.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "d6110a53532e62433131c4b39b98ba7cda2fdc2341344236aaf22ceb422d1adf", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "63916a9ae3ed69d3ec4321da6fe0233e775118810438d0f52ada04dec80e4559", "generation_seconds_batch": 16.429961288929917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6885600090026855, "target_z": 1.1562501136731211, "ce": 5.597680568695068, "genuineness": 3.6287014484405518, "identity": 0.46947720646858215, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d6110a53532e62433131c4b39b98ba7cda2fdc2341344236aaf22ceb422d1adf.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "d68b634c839411682d364e50da5dc7086daeb1a6517b596d8260cbcc4388328f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "84053d6f66219b697c2435166a46ac8a66b84faccb30aa5759c502f85584bfe0", "generation_seconds_batch": 15.359892897075042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9414691925048828, "target_z": -0.8554686671580319, "ce": 6.1020402908325195, "genuineness": 3.9801597595214844, "identity": 0.5887047052383423, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d68b634c839411682d364e50da5dc7086daeb1a6517b596d8260cbcc4388328f.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "d69b529f730d4823afabd2cd7c0aa97a5ce3e10ffd3dfe5c50c1d388654359e1", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4187ebdd1b36466b023bdd16e03a471044be22b31f4238e942e1c589b0866bab", "generation_seconds_batch": 15.547946182079613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3885064125061035, "target_z": -1.4921874908847026, "ce": 5.927301406860352, "genuineness": 4.231201171875, "identity": 0.40649038553237915, "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/vn_VOLT_reg_high/d69b529f730d4823afabd2cd7c0aa97a5ce3e10ffd3dfe5c50c1d388654359e1.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "d6c50c26d6677b1ffe130f555d409d824793a2fd461a79f8b24c7ff80cf73aa8", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9a32906506ddfa8661fa9619a999a0e2760836f71600d6a5ce7ff084e75aae2e", "generation_seconds_batch": 16.581750139943324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.402076005935669, "target_z": -1.4765625412869354, "ce": 6.221180438995361, "genuineness": 4.319066047668457, "identity": 0.5759877562522888, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d6c50c26d6677b1ffe130f555d409d824793a2fd461a79f8b24c7ff80cf73aa8.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "d6e53b59ac9422167417e437878657bf7a9ecee0bb6f14a7ef5d1069495c872f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ba1c5b8844b7d94dd7d4dfd74d5bcaf2d469cf7c5b0affae749e8e8862bd654e", "generation_seconds_batch": 21.895347035024315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.704761266708374, "target_z": 0.02343756166230631, "ce": 6.1894097328186035, "genuineness": 4.356721878051758, "identity": 0.5911386013031006, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d6e53b59ac9422167417e437878657bf7a9ecee0bb6f14a7ef5d1069495c872f.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "d6fbd4244caa8697c46b80f683bb009b67e6aa7ee297d8fdd1c775b1666c2502", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c779c477203da95d3733792d7bf7f21d3b8c4c3734c2b1b897fe4a9205d98bb5", "generation_seconds_batch": 21.350209361989982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.039849042892456, "target_z": -0.7421874394100816, "ce": 6.197352409362793, "genuineness": 4.143336772918701, "identity": 0.35886919498443604, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d6fbd4244caa8697c46b80f683bb009b67e6aa7ee297d8fdd1c775b1666c2502.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "d715afd2eb2d63bc93b32934a8bbd15427ef483b20338741d3def83b8c87121a", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a45005ef309ea3909e8c2f4c22f46839d0b477d9dd99382d4eba126d413d8f94", "generation_seconds_batch": 15.239451398025267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 5.959072113037109, "genuineness": 4.168440818786621, "identity": 0.5978603363037109, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d715afd2eb2d63bc93b32934a8bbd15427ef483b20338741d3def83b8c87121a.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": "d73e4e795d3ba004317432f7d63d4aca6b6f817efb4bc002b804bf981161dc48", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "007a0f461e645e1f642b6d608adefb907e4305d716a5775c503af74e361f129b", "generation_seconds_batch": 15.382084197015502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.350254535675049, "target_z": -0.384765516286673, "ce": 6.109982967376709, "genuineness": 4.036643981933594, "identity": 0.4044130742549896, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de laag en daarna naast het raam neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d73e4e795d3ba004317432f7d63d4aca6b6f817efb4bc002b804bf981161dc48.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "d7b18331b870ac8bc6a4950578f09f3d73488ba6388e93f17d0c3d48e543f356", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5f31e32444d685843cf937f0bc0cc7146ce5c7901bbd6a49611547ed1ef61d61", "generation_seconds_batch": 25.34119206201285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.734532117843628, "target_z": -1.0937500407507417, "ce": 6.23706579208374, "genuineness": 4.494794845581055, "identity": 0.5536569356918335, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d7b18331b870ac8bc6a4950578f09f3d73488ba6388e93f17d0c3d48e543f356.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "d7d2b80902eb636085bd5be9b38453d843bfeec87a022b23931e177bd65b0e80", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "691bc883ffd5212ed85aba8f124401bc46af77a0efb8c35b07429b22363dc80f", "generation_seconds_batch": 20.198364231036976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6182546615600586, "target_z": -0.07617200676966761, "ce": 6.173524379730225, "genuineness": 4.20609712600708, "identity": 0.5588840842247009, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d7d2b80902eb636085bd5be9b38453d843bfeec87a022b23931e177bd65b0e80.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "d7e76fadf89d6b347c9f1291b799714166415cf8a7842b5e99bdea5ec9a19a86", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0bb6a4f0a57b17b7fd88fd986768c8f5ad7d5a8d16278a118ac413a5ca5bcced", "generation_seconds_batch": 16.446868072031066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4970635175704956, "target_z": -1.3671874823055992, "ce": 6.141753673553467, "genuineness": 4.375550270080566, "identity": 0.5740991830825806, "hypothesis": "La porte 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/vn_VOLT_reg_high/d7e76fadf89d6b347c9f1291b799714166415cf8a7842b5e99bdea5ec9a19a86.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "d7f90ef77e84d3355bca929f6bd21892b024d66680720d264f0509d8542468d4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf29c0bb7ac7f431dad5103ab327b0db2c2220e52d2086f608cd82b166daae3f", "generation_seconds_batch": 21.495117209968157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7005207538604736, "target_z": 0.01855474775479714, "ce": 5.772419452667236, "genuineness": 3.760498285293579, "identity": 0.6376525163650513, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d7f90ef77e84d3355bca929f6bd21892b024d66680720d264f0509d8542468d4.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "d817beb7235d81f22616c6dadabcf0b95f6355dc469ed3cc8a3dd5f061796ffa", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6a3eb770b8048755d57576ae04885ea3536ca0b11759ce58a05ff1fb72e8f740", "generation_seconds_batch": 20.35242151201237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7820258140563965, "target_z": -1.0390625798929012, "ce": 5.744620323181152, "genuineness": 4.105680465698242, "identity": 0.44093233346939087, "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/vn_VOLT_reg_high/d817beb7235d81f22616c6dadabcf0b95f6355dc469ed3cc8a3dd5f061796ffa.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "d872f36524090f5ad64d4f98261d045214a1190955eb71ab5c98895524a89db9", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "36b75fe90b4a183c4f5165d03ace2e9612585b8bb3b2e18b6703505b11481fe9", "generation_seconds_batch": 22.403783822082914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4292153120040894, "target_z": -1.4453125048257458, "ce": 6.149696350097656, "genuineness": 4.720732688903809, "identity": 0.7252507209777832, "hypothesis": "La porte 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/vn_VOLT_reg_high/d872f36524090f5ad64d4f98261d045214a1190955eb71ab5c98895524a89db9.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "d89328b032e86d2a8bc97634b15e560c1ba1a11765a5f48bc859c800be9bda2e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8ed368b2a390362cc899ceb680d5d1c5242de22ad0a1e0c1c53fde618aebafd4", "generation_seconds_batch": 22.153891149908304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6487865447998047, "target_z": -0.04101552701055237, "ce": 5.752562999725342, "genuineness": 3.998987913131714, "identity": 0.5829644799232483, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d89328b032e86d2a8bc97634b15e560c1ba1a11765a5f48bc859c800be9bda2e.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "d94afc6a18ca48b8d9015cf485587e4de69f3d811505e0394139009130381375", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94fc9b74c51e22b5786e054d92cb7891f9975134aad692392df653b5d194dc16", "generation_seconds_batch": 21.48652741499245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7413170337677002, "target_z": -1.0859374286862022, "ce": 6.165581703186035, "genuineness": 4.331617832183838, "identity": 0.6071256399154663, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d94afc6a18ca48b8d9015cf485587e4de69f3d811505e0394139009130381375.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "d94fdf2141271c5c802dca8905e1f3ae502ac0637138784525bc99c04649d004", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1051a4cf36c0f58600d999498bb3f4b7a0ff22995f89b4c8f0d3f72cf0d421a3", "generation_seconds_batch": 15.041157491970807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6259750127792358, "target_z": -1.218750049329845, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.47897017002105713, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/d94fdf2141271c5c802dca8905e1f3ae502ac0637138784525bc99c04649d004.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "d99491a75ddc036f4fc98e75ed34ed2d37b838c0546b9506d53acb949832ce00", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "39950bac478e60189071a1ef3e0b03dab9c5e68c7b4a9d2fe149fad18d6a18aa", "generation_seconds_batch": 19.918218408012763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.945622205734253, "target_z": 0.3007811719837777, "ce": 5.935244083404541, "genuineness": 3.9927117824554443, "identity": 0.600866973400116, "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/vn_VOLT_reg_high/d99491a75ddc036f4fc98e75ed34ed2d37b838c0546b9506d53acb949832ce00.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "da773c0632bd99a1abc5c24dd427aa7837c69a6663ead59b198097f1e2747135", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c3ca033b03de3d2021c2f1d3def47e8044825949559428cd50c6dce91aa4852f", "generation_seconds_batch": 28.30564015498385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.485102653503418, "target_z": -0.2294922536529308, "ce": 6.038498878479004, "genuineness": 3.986435890197754, "identity": 0.751716673374176, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/da773c0632bd99a1abc5c24dd427aa7837c69a6663ead59b198097f1e2747135.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "da9e971f52737639c6acc63836d7cbd6fc57985b4c8850d7653f027dda014684", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d3c08fed531f95e17312e8ad698f08c3a38b248557e98637300e42337699807c", "generation_seconds_batch": 16.062222703010775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5038483142852783, "target_z": -1.3593750075067155, "ce": 6.173524379730225, "genuineness": 4.344170093536377, "identity": 0.5401853322982788, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/da9e971f52737639c6acc63836d7cbd6fc57985b4c8850d7653f027dda014684.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "dab5a4bd4340768e35045cbbf478ba9207402d894e2aa432d2c0667172b3ef84", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e1b8672a2510983078068157e43b94ae1d63ad12b4084756de38d9bbc792a90f", "generation_seconds_batch": 20.534251290024258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.598835825920105, "target_z": -1.249999948525379, "ce": 6.2767791748046875, "genuineness": 4.519899368286133, "identity": 0.686606764793396, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/dab5a4bd4340768e35045cbbf478ba9207402d894e2aa432d2c0667172b3ef84.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "f5400f10cdad5e71cfec02ead8d23398164fe5bca0f32db043799df75bbb4e6e", "generation_seconds_batch": 15.190722496947274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.292664527893066, "genuineness": 4.099404335021973, "identity": 0.3527412414550781, "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/vn_VOLT_reg_high/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "db3133c2a0fc69c7cbd16d580f9faf841d9d08aa1139d2d0ed11725c18595072", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1b434460c81789e0e3687e7ca9232e9b80192a4fb667d198f39a11dabd9a9b3a", "generation_seconds_batch": 15.338143707020208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6259750127792358, "target_z": -1.218750049329845, "ce": 6.348263263702393, "genuineness": 4.068024158477783, "identity": 0.5903900861740112, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/db3133c2a0fc69c7cbd16d580f9faf841d9d08aa1139d2d0ed11725c18595072.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "db3cd54eada5960b256359675d0453ee638356ec4bc70218fc6ee9d297fbe689", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5552f96c689452b13d6d07a4f38d5ba0fedd5cd008db77064c59739cd3c9dd3a", "generation_seconds_batch": 21.895347035024315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.423952102661133, "target_z": 0.8515626356570739, "ce": 5.71682071685791, "genuineness": 3.8797430992126465, "identity": 0.5540236234664917, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/db3cd54eada5960b256359675d0453ee638356ec4bc70218fc6ee9d297fbe689.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "db5879301c13952ee57b2e6b275a4777ed5c050e58f7e519285befaad62502de", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ef67a7a69ec2580c9326bfdd3ea7cdc65740225d3e2a484d391e45ba7d021c75", "generation_seconds_batch": 20.242440949077718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6071419715881348, "target_z": 1.0624998670238959, "ce": 5.589737892150879, "genuineness": 3.487490653991699, "identity": 0.32570263743400574, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/db5879301c13952ee57b2e6b275a4777ed5c050e58f7e519285befaad62502de.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "dba13454e63d98e99303da940f0ad6aa0e549ea2bc447d98927e256fc574962b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7984d1a80fae6e6da6eff30c44bd214ec9ef2bedbb1f9b40433965af8e93c4df", "generation_seconds_batch": 21.539494332973845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8668360710144043, "target_z": -0.9414063017427179, "ce": 6.173524379730225, "genuineness": 3.986435890197754, "identity": 0.5718252658843994, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/dba13454e63d98e99303da940f0ad6aa0e549ea2bc447d98927e256fc574962b.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "dbd200d8b33b32ebdace1e136dfe6a1f6d21f0093d8c55596e324b03ef146262", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8f8dc6f259122a31cd766fb906017c077863bb50205719c09f173a225ffa64d8", "generation_seconds_batch": 20.693806312978268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9448615312576294, "target_z": -0.8515624983914181, "ce": 5.982900142669678, "genuineness": 4.080576419830322, "identity": 0.507246732711792, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/dbd200d8b33b32ebdace1e136dfe6a1f6d21f0093d8c55596e324b03ef146262.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": "dd30d7f1b1ef65492ee52cc261dd9ca23a231a40243048eab3f36710370b1786", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The road turns left behind the bridge.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7708422a052753fd4895d46afef41b8dcdc2102abaec11ff75180cfa1be90922", "generation_seconds_batch": 23.278354109963402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.043241500854492, "target_z": -0.738281133377812, "ce": 6.324435234069824, "genuineness": 4.162164688110352, "identity": 0.5134491324424744, "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/vn_VOLT_reg_high/dd30d7f1b1ef65492ee52cc261dd9ca23a231a40243048eab3f36710370b1786.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": "dd35d671e6eb17a06e5b79345ca0351363b254542203e0cd8ff622eca72c2f13", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c723d66801ef5ed8ff7e82cdb0595c6dff327beb09f2a90e104f500674501dff", "generation_seconds_batch": 13.876918382011354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9991400241851807, "target_z": -0.7890625627346942, "ce": 5.998785495758057, "genuineness": 4.143336772918701, "identity": 0.6215790510177612, "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/vn_VOLT_reg_high/dd35d671e6eb17a06e5b79345ca0351363b254542203e0cd8ff622eca72c2f13.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "ddfa4c248d34ac3ddd5f8d87251415c7fbb97aa5c83e9c17ceb19b66faf77b5e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7e229f7c837d0cb362f50f53b7a582cb19ac9d597759f0416f1e3e364616b453", "generation_seconds_batch": 23.42366203002166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2298238277435303, "target_z": -0.5234375959787203, "ce": 6.054384231567383, "genuineness": 3.9173994064331055, "identity": 0.7041950225830078, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ddfa4c248d34ac3ddd5f8d87251415c7fbb97aa5c83e9c17ceb19b66faf77b5e.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "de44b412b01ec31278c7d1c2db10908abbcf90b735b0871eaa291f4226a792bb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "666a7273d4cce20cdd2b1b18dfd6969efb238c17d76e092d994bc4667cc87ae5", "generation_seconds_batch": 21.1457587829791, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4088608026504517, "target_z": -1.468750066488052, "ce": 6.443574905395508, "genuineness": 4.080576419830322, "identity": 0.552832305431366, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/de44b412b01ec31278c7d1c2db10908abbcf90b735b0871eaa291f4226a792bb.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "dee209de95424fa025088352b285034bf3c09439cacf33d9d2d6ba444a8c9202", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2d5944ed0d933db5056708297263ab3bb7d4e4743df0ea385a7b70d2979f1561", "generation_seconds_batch": 23.80443933303468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6148624420166016, "target_z": -0.08007803827062569, "ce": 5.911416053771973, "genuineness": 3.7291181087493896, "identity": 0.620549738407135, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/dee209de95424fa025088352b285034bf3c09439cacf33d9d2d6ba444a8c9202.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "df6628f024a81b426b166cc001cbae754f3359cecfdd03cb41375a6adcba652e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "982d2a9e94a6fd2459ce39f112e675208dddf477c1c3558bc8f355f90f0b1136", "generation_seconds_batch": 21.37899062805809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5053696632385254, "target_z": 0.945312333243676, "ce": 6.046441555023193, "genuineness": 3.2772433757781982, "identity": 0.6085082292556763, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/df6628f024a81b426b166cc001cbae754f3359cecfdd03cb41375a6adcba652e.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "dfa3aa61f70008c92631b1f034735afa1af834d7abe7d205e286ccfc7c367618", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4404aeee9d5cf7da4d29fae0673fae57f689f989de6fe0be827c36c701d23cff", "generation_seconds_batch": 15.437579977093264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6666839122772217, "target_z": -1.1718750632708883, "ce": 6.316492557525635, "genuineness": 4.419482707977295, "identity": 0.28773415088653564, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/dfa3aa61f70008c92631b1f034735afa1af834d7abe7d205e286ccfc7c367618.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "dfcc72b43107949bca4b49bb95fb2fe2e3f30e5f99c56593e1eb9bd143f394ec", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1978c135689fd1a5e6937c72b7cab59224dad5965dd1d9d54789373d1be415d", "generation_seconds_batch": 20.51522768905852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7481017112731934, "target_z": -1.0781250911529745, "ce": 5.919358730316162, "genuineness": 4.20609712600708, "identity": 0.5685623288154602, "hypothesis": "La porte 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/vn_VOLT_reg_high/dfcc72b43107949bca4b49bb95fb2fe2e3f30e5f99c56593e1eb9bd143f394ec.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "dfd5aa0631b4b6b3f8dc0048d51407b854dbabb9c723128241e2dda18244eb33", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "50c68f1a62b9b15fb4648ca2ef53c3b8587b9e61e1e00ed134e1c0d56ea92cdc", "generation_seconds_batch": 14.804364953073673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.768456220626831, "target_z": -1.0546875294906681, "ce": 6.086154937744141, "genuineness": 4.20609712600708, "identity": 0.6350935101509094, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/dfd5aa0631b4b6b3f8dc0048d51407b854dbabb9c723128241e2dda18244eb33.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "dff2a1ce1393ac9b062f727cc7e633fca31386e56318f98a91a3a74a3d424713", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8df35b8dde6ba55c032d77c357d569d698e5dcb8058e1e9393b98b28a82b4692", "generation_seconds_batch": 22.059162570978515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.866748809814453, "target_z": 0.2099609980228941, "ce": 6.070269584655762, "genuineness": 4.231201171875, "identity": 0.5200756788253784, "hypothesis": "La porte 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/vn_VOLT_reg_high/dff2a1ce1393ac9b062f727cc7e633fca31386e56318f98a91a3a74a3d424713.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": "e0c7839e6302d0ca7fb91a50b891bb216471fee470d5e6030f4dd1e4269f3228", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "9f495e798a22a84b1725cf5f3f3ccd96160b1d7d52bab10a95bf163457761e68", "generation_seconds_batch": 14.643346751923673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.03645658493042, "target_z": -0.7460937454423513, "ce": 6.078212261199951, "genuineness": 4.231201171875, "identity": 0.6258554458618164, "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/vn_VOLT_reg_high/e0c7839e6302d0ca7fb91a50b891bb216471fee470d5e6030f4dd1e4269f3228.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "e0cf80f5ea9bd512ddbd5948cdb77a1a9b4e30169e69e47e6286be48fde1b432", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f41b59a462df350a913bc307bbf6e0005e7e8b71706a023dbf855d72249c6c5f", "generation_seconds_batch": 20.43929201492574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6191902160644531, "target_z": -1.2265625241287286, "ce": 5.871703147888184, "genuineness": 4.268857479095459, "identity": 0.6153019666671753, "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/vn_VOLT_reg_high/e0cf80f5ea9bd512ddbd5948cdb77a1a9b4e30169e69e47e6286be48fde1b432.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "e0efd95013adcde26b1c71c0cca1e470359f723d64873e28bb21bed998870ee2", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0ee338a7e2afc4229e5248c53dcf3d94c2daed1cf2be8bd057549995e529c22d", "generation_seconds_batch": 15.793302399921231, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.436000108718872, "target_z": -1.437500030026862, "ce": 6.213237762451172, "genuineness": 4.15588903427124, "identity": 0.7221260070800781, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e0efd95013adcde26b1c71c0cca1e470359f723d64873e28bb21bed998870ee2.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "e0f2ff7631cc85251ce5e8b0fd6660ddad88f581a1c55a85549f79fab33efd25", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "92356f76e06d6edba72323a42cdd47c976edd11ef562f421021e7ac2407d7910", "generation_seconds_batch": 16.581750139943324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6463295221328735, "target_z": -1.1953124876675387, "ce": 6.2767791748046875, "genuineness": 4.419482707977295, "identity": 0.5739439129829407, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e0f2ff7631cc85251ce5e8b0fd6660ddad88f581a1c55a85549f79fab33efd25.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "e1873b64dfe0bdef560756dcaed7610809791a041adfdd18fc8ba610fcd724df", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e1bfe835dc878889c959177356dbd992204c9d8d632f9f4a0b50dea24d75082a", "generation_seconds_batch": 19.492545088985935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5581269264221191, "target_z": -1.296874934584336, "ce": 6.300607204437256, "genuineness": 4.400654315948486, "identity": 0.4527921676635742, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e1873b64dfe0bdef560756dcaed7610809791a041adfdd18fc8ba610fcd724df.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "e19fb8b4c26b104b821ec225bb1b998a6fcf607d6e4f88188be6b1616a2d7b87", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2ec80b27c64b5642347c52879ab212aeb5f491cf0f3420dd67fb38b46ebf7ec0", "generation_seconds_batch": 14.575587228988297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9889628887176514, "target_z": -0.8007812063001916, "ce": 6.213237762451172, "genuineness": 3.7918784618377686, "identity": 0.22770430147647858, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "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/vn_VOLT_reg_high/e19fb8b4c26b104b821ec225bb1b998a6fcf607d6e4f88188be6b1616a2d7b87.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "e1c3c7da7eb1f6a27af161fbe857fd95c288d3c5efb738bfa9e66e0648d75f47", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 129, "seconds_generated": 10.32, "mp3_sha256": "5d5cceeee7f7aef6a6c2754fe2018508980810d2d1ff571fd327be1ddce3129c", "generation_seconds_batch": 20.43950641003903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4699242115020752, "target_z": -1.3984375187667888, "ce": 6.117925643920898, "genuineness": 4.645420074462891, "identity": 0.8622764348983765, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e1c3c7da7eb1f6a27af161fbe857fd95c288d3c5efb738bfa9e66e0648d75f47.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "e1dec60f2aa980b88f48559314d90c56725afbebfa653ddafc9090e4dd08a01c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "35e00b37b789ded441b594ecd53c7fa11f21287b4e608dff7ecc4560b3723c12", "generation_seconds_batch": 21.35887040407397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1661288738250732, "target_z": 0.5546874951742543, "ce": 5.7128496170043945, "genuineness": 3.5847692489624023, "identity": 0.6392056941986084, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e1dec60f2aa980b88f48559314d90c56725afbebfa653ddafc9090e4dd08a01c.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "e20aea821f1b8f352bbfabfeec23563d2b311de3dff32efc1ce1975e43ae90fd", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "495a18fc6ed6e5fb9232634820094c7c8645dfd8e64bf65f2d01520996612913", "generation_seconds_batch": 21.465773788979277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6666839122772217, "target_z": -1.1718750632708883, "ce": 6.078212261199951, "genuineness": 4.6203155517578125, "identity": 0.628044068813324, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e20aea821f1b8f352bbfabfeec23563d2b311de3dff32efc1ce1975e43ae90fd.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "e20d05957e92857ecec941f24f0e2362a86f1156bf73079a0435098abfb6ff9c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "21022ced0d1d6a82346b33e1c3d23dec2861bb1ac248aa4f130a29c077ba9802", "generation_seconds_batch": 15.440019160043448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.693823218345642, "target_z": -1.1406250268096985, "ce": 5.967014789581299, "genuineness": 4.162164688110352, "identity": 0.5595188736915588, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e20d05957e92857ecec941f24f0e2362a86f1156bf73079a0435098abfb6ff9c.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "e24e53245073381f0abe189370bc5e0299bf814d719fcd217ecf91ea6ad3a129", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3f739ccac4065af3003de04f834f443ceb85f91b80c5a36e0d4948687f4e3665", "generation_seconds_batch": 15.227561134030111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.707392930984497, "target_z": -1.1249999399462756, "ce": 6.205295085906982, "genuineness": 4.507347106933594, "identity": 0.3775607943534851, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e24e53245073381f0abe189370bc5e0299bf814d719fcd217ecf91ea6ad3a129.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "e2591fafd5c4a52386bbc4b631b6fb50158fe09a546034c1186baa1edab33bd0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0d21fcc93a950a25648579286b5cb502767785b65ad66cdc310b2b5dc722ffff", "generation_seconds_batch": 21.48652741499245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348558187484741, "target_z": -0.38671880656846364, "ce": 6.141753673553467, "genuineness": 4.2751336097717285, "identity": 0.7159101366996765, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e2591fafd5c4a52386bbc4b631b6fb50158fe09a546034c1186baa1edab33bd0.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "e2a7f3701c09473dac9c0bae53ce72933c2d16d326cc81f8e27b1fdb2c55fa92", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "74577239d2c48b80a85ae2371a9ec6b40996dc5906781452636551af2b3dbb87", "generation_seconds_batch": 15.359892897075042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3553431034088135, "target_z": -0.3789061945039243, "ce": 6.09409761428833, "genuineness": 3.8797430992126465, "identity": 0.6655157804489136, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e2a7f3701c09473dac9c0bae53ce72933c2d16d326cc81f8e27b1fdb2c55fa92.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "e2d64c4c75c57ef38d85a0960ae72393311cb4cde6b3fa2d9ee15c2c0f4e35af", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cf701bf3d465256adcf4d018df5222902d2e3842e2b00c530a5cd58144e84839", "generation_seconds_batch": 19.96876279998105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8837981224060059, "target_z": -0.9218750461126812, "ce": 6.324435234069824, "genuineness": 4.607763767242432, "identity": 0.5482993721961975, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e2d64c4c75c57ef38d85a0960ae72393311cb4cde6b3fa2d9ee15c2c0f4e35af.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "e30656ae0c4055eec27fdb71f1dae1ad3fd72765c4004e0d647167977417d031", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "463b8f506de15a1571f58374a61df8ce2af406e936644bc74ad2301062aa67a6", "generation_seconds_batch": 22.49146471603308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0500261783599854, "target_z": -0.7304687958445842, "ce": 6.149696350097656, "genuineness": 4.337893962860107, "identity": 0.6049283742904663, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e30656ae0c4055eec27fdb71f1dae1ad3fd72765c4004e0d647167977417d031.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "e3430b7c32cd2445ab49ea9738dce756fde4aeb8c8bfdac3c4551262bc58e1da", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5a2af90c60d86172f01b0454206483f7d0a8154a0e4709810c4fe46cba15f01e", "generation_seconds_batch": 14.698394011938944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9923553466796875, "target_z": -0.796874900267922, "ce": 6.173524379730225, "genuineness": 4.168440818786621, "identity": 0.6028413772583008, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e3430b7c32cd2445ab49ea9738dce756fde4aeb8c8bfdac3c4551262bc58e1da.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": "e3e2595ad4777a8a4c91694bd2ceb1f2b51cf70f3570812e6251a605cde610b9", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b8fcdb4daf3d76453dadd2e39bf144eeb00e770494d183ca836e402b58046809", "generation_seconds_batch": 22.51194363005925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9855704307556152, "target_z": -0.8046875123324613, "ce": 6.125868320465088, "genuineness": 4.030367851257324, "identity": 0.3836766481399536, "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/vn_VOLT_reg_high/e3e2595ad4777a8a4c91694bd2ceb1f2b51cf70f3570812e6251a605cde610b9.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "e40aaf0ef347b8e431c73e527225eaabd8f98d87e87bcde967bc6f2be8e1a56c", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37b6bd27d7bccd67668fe5bbd02f8b957714ec4a37bf9e687336f7c205f3171e", "generation_seconds_batch": 20.90958300291095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1729137897491455, "target_z": 0.5625001072387936, "ce": 5.772419452667236, "genuineness": 3.9048471450805664, "identity": 0.6133559942245483, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e40aaf0ef347b8e431c73e527225eaabd8f98d87e87bcde967bc6f2be8e1a56c.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "e460a0f9e9dcb3daf06219a9b33711165ef09be7a54b09ce13601d80b3261483", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "41e7b2aa9d9a6f1737cc295bd67beef3cb964fe3d61d4d4d9c63a0aa2fd681d6", "generation_seconds_batch": 21.675333639024757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.109982967376709, "genuineness": 4.281409740447998, "identity": 0.6938444375991821, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e460a0f9e9dcb3daf06219a9b33711165ef09be7a54b09ce13601d80b3261483.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "e57319cd4a22fa9889ecae6a6e5b9694f647b61e6090c00fa2c453715f1b6756", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fd8846ce34d7aa0729b0fc99b3e743108b6011c2b9049fb14aeae5af8598006d", "generation_seconds_batch": 15.105598498950712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.768456220626831, "target_z": -1.0546875294906681, "ce": 6.284721851348877, "genuineness": 4.218649387359619, "identity": 0.6468300223350525, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e57319cd4a22fa9889ecae6a6e5b9694f647b61e6090c00fa2c453715f1b6756.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "e576e1022ceeb28f05ad4639164ef34c45585bd1201a2fde9a1c53b16217de8a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d6ba09a87d2ebf56f68bb2f859befb9ab7fe7a49cdccd6490129861604366dfd", "generation_seconds_batch": 21.498521744972095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.273925304412842, "target_z": -0.472656166621838, "ce": 5.959072113037109, "genuineness": 4.375550270080566, "identity": 0.4121340811252594, "hypothesis": "La porte 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/vn_VOLT_reg_high/e576e1022ceeb28f05ad4639164ef34c45585bd1201a2fde9a1c53b16217de8a.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "e603c1c48d88e08f2b0177a3a0914d2d5afc4a89d0782a485f16c0492c9af35a", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3c5f6de64e78d21bbeee8050b4564fb26fc8e35e79ee5ee50d85a5b82dc4771e", "generation_seconds_batch": 21.464936139062047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.707392930984497, "target_z": -1.1249999399462756, "ce": 6.022613525390625, "genuineness": 4.457139015197754, "identity": 0.6901024580001831, "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/vn_VOLT_reg_high/e603c1c48d88e08f2b0177a3a0914d2d5afc4a89d0782a485f16c0492c9af35a.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "e616917c89c59f3a754558fef751c8708e58ac668bfe23be9d48fb76c3bc734d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "14fd3906c1064cea8c5314e62fc32673d19e20d7449b3b6b4278e9441724a521", "generation_seconds_batch": 20.84233006404247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8091652393341064, "target_z": -1.0078124061660556, "ce": 5.363371849060059, "genuineness": 3.7165660858154297, "identity": 0.3738524615764618, "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/vn_VOLT_reg_high/e616917c89c59f3a754558fef751c8708e58ac668bfe23be9d48fb76c3bc734d.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "e649d36025ff702fe50ffa3ef58c50e84af6c8d53be6ccf25a9759cf952611f5", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1aa8dfeca3189253cc7a78c842a372b4a3bd854c88ec65a5df55ce011354b400", "generation_seconds_batch": 15.273370073991828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7752411365509033, "target_z": -1.046874917426129, "ce": 6.181467056274414, "genuineness": 4.243753433227539, "identity": 0.3506561517715454, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e649d36025ff702fe50ffa3ef58c50e84af6c8d53be6ccf25a9759cf952611f5.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "e68113dd7058e1c7f5a8076c5249b9391ed1b5d77c6d935ea910c70618d93e8d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "876227139ed1bd98529fc97a370b2ed72d3ff9587c5ba78d74ca41643990f6db", "generation_seconds_batch": 21.760832691099495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3900279998779297, "target_z": 0.8125001243970006, "ce": 5.752562999725342, "genuineness": 3.6914620399475098, "identity": 0.5477575063705444, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e68113dd7058e1c7f5a8076c5249b9391ed1b5d77c6d935ea910c70618d93e8d.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "e6a089fa0d0e5e5903bf2a20e0f957694424044148fa56da2237c71bca8ad491", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P06", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Begin with the quality contained, then let it become clearly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d71942ab3965dee074e0111fa638294a9ab852d6200c1920e4272ce0ecf1694", "generation_seconds_batch": 15.440019160043448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9278994798660278, "target_z": -0.8710937540214547, "ce": 6.109982967376709, "genuineness": 4.3504462242126465, "identity": 0.6953139305114746, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e6a089fa0d0e5e5903bf2a20e0f957694424044148fa56da2237c71bca8ad491.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": "e6d14d7ae6641427e34d911c5ad6a51eb2936e14a94a55c599e38362506c9c3e", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I wrote the number on the envelope.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "58f3f36e55ffa0d46c1bf302e86d2af3e32d19d0a86c0ab264ea06cc77005b2d", "generation_seconds_batch": 22.90175666299183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1721529960632324, "target_z": -0.589843700402058, "ce": 6.205295085906982, "genuineness": 3.5973212718963623, "identity": 0.44601529836654663, "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": 0.120000000000001, "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/vn_VOLT_reg_high/e6d14d7ae6641427e34d911c5ad6a51eb2936e14a94a55c599e38362506c9c3e.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "e6e840302e6e5b93794971f3891cc62ddfb0fcce926f144a89dfca05cee3229e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b07b5ba07cf808c355011b62085dd2dd7cdd7883afccb9147b9a1a2dc3990ee6", "generation_seconds_batch": 19.300972762983292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4088608026504517, "target_z": -1.468750066488052, "ce": 6.205295085906982, "genuineness": 4.545003414154053, "identity": 0.736880898475647, "hypothesis": "La porte 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/vn_VOLT_reg_high/e6e840302e6e5b93794971f3891cc62ddfb0fcce926f144a89dfca05cee3229e.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "774a31c294db3672137295a32380563a43779fa62981b44bd849ef73863a595f", "generation_seconds_batch": 15.457568651996553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7277473211288452, "target_z": -1.1015625155496251, "ce": 6.4515180587768555, "genuineness": 4.419482707977295, "identity": 0.3041272759437561, "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/vn_VOLT_reg_high/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "e747f479f982a08cef7598cf56dc50394317e7706dd0774fafef0dba505de9f8", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1543674b7cd8903ddfdb31cbbb6b318d130534d06a69fda0e7880228833be60c", "generation_seconds_batch": 21.350209361989982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.246785879135132, "target_z": -0.5039063403486836, "ce": 6.022613525390625, "genuineness": 3.9927117824554443, "identity": 0.3904503583908081, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e747f479f982a08cef7598cf56dc50394317e7706dd0774fafef0dba505de9f8.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "e7eace92e1837d702db631e1e23ba63d3e8cf30dc016f4ce7f95ad26ec6f8fd2", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eaeb87b0884bd02beb7f336e816f67cac2b11d43b8d8d14e21765838aaada8ee", "generation_seconds_batch": 22.429413801059127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7481017112731934, "target_z": -1.0781250911529745, "ce": 5.959072113037109, "genuineness": 4.231201171875, "identity": 0.527867317199707, "hypothesis": "La porte 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/vn_VOLT_reg_high/e7eace92e1837d702db631e1e23ba63d3e8cf30dc016f4ce7f95ad26ec6f8fd2.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": "e809e9790e0a6f630c744e6f63a0de2430ac9158461e1885b0c67f3baf08f4ac", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a9386362defa02f72cc9f4547fff93a8e43db49dbc0c2ac2eadad60cd1a6ee1", "generation_seconds_batch": 22.51194363005925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5563433170318604, "target_z": -0.1474609251005145, "ce": 6.141753673553467, "genuineness": 3.986435890197754, "identity": 0.44569918513298035, "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/vn_VOLT_reg_high/e809e9790e0a6f630c744e6f63a0de2430ac9158461e1885b0c67f3baf08f4ac.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "e8147ed50836f1cb406fe32c460f6506b74175a582c6ae50625117c5787228f0", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2c7ca223cfd9821d4b9d25a45d89e662d38ee3bcd227ee0e2a7356821f2ab88b", "generation_seconds_batch": 15.547381401993334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5445572137832642, "target_z": -1.3125000214477587, "ce": 5.649308204650879, "genuineness": 4.13078498840332, "identity": 0.5396026372909546, "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/vn_VOLT_reg_high/e8147ed50836f1cb406fe32c460f6506b74175a582c6ae50625117c5787228f0.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "e824ff6dce66373f57941c55a4f87916b3e2c43a6df6e02de38e1f01cd38caba", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P02", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Use breath, pitch movement, consonant attack and release to realize the requested quality.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ccd491199d16284520e7f7b08a2493106037a328d093c43822631f769bfcdb97", "generation_seconds_batch": 14.634186455979943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6124054193496704, "target_z": -1.234374998927612, "ce": 6.523001670837402, "genuineness": 4.65797233581543, "identity": 0.1417718529701233, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e824ff6dce66373f57941c55a4f87916b3e2c43a6df6e02de38e1f01cd38caba.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "e8466a0576dc2a5a614b1653d54834fbd5869c7dd50b18a69429077b02f8a328", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "52a26f076e816e81e72e135a5129f29a4697157095feacdd63c3508bf1b3acc7", "generation_seconds_batch": 21.536784865078516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3885064125061035, "target_z": -1.4921874908847026, "ce": 6.046441555023193, "genuineness": 4.557555198669434, "identity": 0.6933602690696716, "hypothesis": "La porte 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/vn_VOLT_reg_high/e8466a0576dc2a5a614b1653d54834fbd5869c7dd50b18a69429077b02f8a328.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": "e8780a011d6fc8ebb87046e6a05f9d0955c32ccb11601428f98d0c0d2621ca02", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Someone moved the little blue chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "809a1f03d531448744d1e26fb4a31f771d4734bf0d6e5216cef2b03617755650", "generation_seconds_batch": 15.504482486983761, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.039849042892456, "target_z": -0.7421874394100816, "ce": 6.252951145172119, "genuineness": 4.218649387359619, "identity": 0.25808513164520264, "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/vn_VOLT_reg_high/e8780a011d6fc8ebb87046e6a05f9d0955c32ccb11601428f98d0c0d2621ca02.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "e8beb87037c9bc74557cd226ea0b0f5de056bf9481aea5b9480b292e6f242663", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "20880715454b23aaa40cca5dbb920542cbec15f968d12466bee147f007e77da2", "generation_seconds_batch": 14.80648051307071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2392404079437256, "target_z": -1.6640624855227628, "ce": 6.006728172302246, "genuineness": 3.9425034523010254, "identity": 0.482383131980896, "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/vn_VOLT_reg_high/e8beb87037c9bc74557cd226ea0b0f5de056bf9481aea5b9480b292e6f242663.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "e920d49a7a185d2e10ac33003d6ceb80573dd0c58b01ee0e0cd80784683a3cfa", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7c3c7eb947a61599e853a94bed584643cb9ba3693fefff1eacda9c14bde878b4", "generation_seconds_batch": 22.73613178404048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7616714239120483, "target_z": -1.0625000042895518, "ce": 6.0305562019348145, "genuineness": 4.268857479095459, "identity": 0.6692146062850952, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e920d49a7a185d2e10ac33003d6ceb80573dd0c58b01ee0e0cd80784683a3cfa.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "e9b5d1ad90196231e20e32671f783c7b1e66353fb2ff1f8f26f3062d80477b48", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ecd42206e058da1503e5851bdb5827adbb93fb34c87a6e24438ca012856bfc24", "generation_seconds_batch": 15.908738080062903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.524202823638916, "target_z": -1.3359374458444093, "ce": 6.252951145172119, "genuineness": 4.18099308013916, "identity": 0.6712496876716614, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e9b5d1ad90196231e20e32671f783c7b1e66353fb2ff1f8f26f3062d80477b48.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "e9b7bcab1dac2754a69c20e883b46844ed9dc4eb17ef2f705d23ad1d639fca55", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6cdec2ced73e644684293cddd101a4c13a7321d18333f270ff2299832b4e3f5b", "generation_seconds_batch": 22.287601656047627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.7496232986450195, "target_z": 1.2265625241287286, "ce": 4.9602813720703125, "genuineness": 3.500042676925659, "identity": 0.42874667048454285, "hypothesis": "La porte 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/vn_VOLT_reg_high/e9b7bcab1dac2754a69c20e883b46844ed9dc4eb17ef2f705d23ad1d639fca55.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "0e4f8b6150df4ef16f48557cf6fc2e103bc06631744024287fee5097e592ca8d", "generation_seconds_batch": 14.91730610805098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.58526611328125, "target_z": -1.2656250353888019, "ce": 6.38797664642334, "genuineness": 4.444586753845215, "identity": 0.48639458417892456, "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/vn_VOLT_reg_high/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "e9eec92e84875c1af320a131d2794ff18f38789085b2b58f4744f74b0dd2301d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b6ee3cd2257f5175444307d0d8b4f67fdd5008cc7cf40ce86d6f64748f4d2e76", "generation_seconds_batch": 21.8067792650545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8565714359283447, "target_z": 0.1982420799260852, "ce": 5.998785495758057, "genuineness": 3.873466968536377, "identity": 0.4526786208152771, "hypothesis": "De deur staat ze nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/e9eec92e84875c1af320a131d2794ff18f38789085b2b58f4744f74b0dd2301d.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "ea071cd11710195ea6d2a1880151a87380df2b8e605628461968277c9e937d04", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f8e8264ff3538495b81158907029ad09a5e99e318ae5d3b393ab6953422c60dc", "generation_seconds_batch": 14.874036789056845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4970635175704956, "target_z": -1.3671874823055992, "ce": 5.621508598327637, "genuineness": 3.9173994064331055, "identity": 0.43359047174453735, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ea071cd11710195ea6d2a1880151a87380df2b8e605628461968277c9e937d04.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "ea098bc85c7530e3ed471a7ea109718d132a5f2bd6dfe3ac20d4ebee3c2198fc", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "21da850bfb8780e3ff925838899c06e36132fa9a29040232b1c8f43161d15e44", "generation_seconds_batch": 14.133097704965621, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.134836435317993, "target_z": -0.6328125176944009, "ce": 6.252951145172119, "genuineness": 4.281409740447998, "identity": 0.70136559009552, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ea098bc85c7530e3ed471a7ea109718d132a5f2bd6dfe3ac20d4ebee3c2198fc.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": "ea09908ee3dc7421f25f87bfd2ff25e92cc71f118add295bcf540d503a600106", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I wrote the number on the envelope.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ecb71ea181c1052b6a82ba231b5e1cbafbcd0579635365bfb34aab45603b73bc", "generation_seconds_batch": 22.90175666299183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1212668418884277, "target_z": -0.648437467292168, "ce": 6.2767791748046875, "genuineness": 3.7291181087493896, "identity": 0.4685617685317993, "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/vn_VOLT_reg_high/ea09908ee3dc7421f25f87bfd2ff25e92cc71f118add295bcf540d503a600106.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "eb323cce5cb79585d60570a05289b8a6383cafcbe3b79d675e7ca64489d7e445", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "829684677760cafa88acc80b019cb84b391df5d7f29d19e1a1d9f6cd9cc499fe", "generation_seconds_batch": 19.141490117996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0534186363220215, "target_z": -0.7265624898123146, "ce": 6.332377910614014, "genuineness": 4.306513786315918, "identity": 0.7150030136108398, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/eb323cce5cb79585d60570a05289b8a6383cafcbe3b79d675e7ca64489d7e445.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "eb6e919af9a74c99ba5cc3b65cee824f2c1ce78c88a54240134953d6dede86fe", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e7d230a5f48b4dea1c4328a517461760fe066d7cd752584b5842a3403cbe5a8f", "generation_seconds_batch": 20.761833520955406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4970635175704956, "target_z": -1.3671874823055992, "ce": 5.935244083404541, "genuineness": 4.331617832183838, "identity": 0.7887148857116699, "hypothesis": "La porte 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/vn_VOLT_reg_high/eb6e919af9a74c99ba5cc3b65cee824f2c1ce78c88a54240134953d6dede86fe.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": "eb7967c69e5a77cc8d29cf08b2c22b55dba489247d2799525ea14fc60f2b0876", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Escribí el número en el sobre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f3735d49b8fa24fcfee2ee6f8ab2bda4b3d8ee40e63d8c980299cad189110604", "generation_seconds_batch": 20.529932930949144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9991400241851807, "target_z": -0.7890625627346942, "ce": 5.974957466125488, "genuineness": 4.036643981933594, "identity": 0.6076117753982544, "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/vn_VOLT_reg_high/eb7967c69e5a77cc8d29cf08b2c22b55dba489247d2799525ea14fc60f2b0876.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "d807460dc3965a0ed6b0172db9a79a0c3c68ea7daa4897da581d8403c7d261be", "generation_seconds_batch": 16.634022359969094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6191902160644531, "target_z": -1.2265625241287286, "ce": 6.205295085906982, "genuineness": 4.344170093536377, "identity": 0.8865240812301636, "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/vn_VOLT_reg_high/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.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": "ebf6e53feb8501828cd1b28d2e0f9d390c484114dcb1cac6b81207313b469d99", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8fb2f599c435b90f28a5452e612468539043f84fe9cb139af89a75a77e4dc527", "generation_seconds_batch": 20.920846708933823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.622495174407959, "target_z": -0.07128919286215844, "ce": 6.1894097328186035, "genuineness": 3.911123275756836, "identity": 0.3779660761356354, "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/vn_VOLT_reg_high/ebf6e53feb8501828cd1b28d2e0f9d390c484114dcb1cac6b81207313b469d99.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": "ec0e943297ee7a23d1fcbb9cb60c9196b0d2bbd0140a91981b99eefbc80a1986", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The keys are on the kitchen table.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "6ae4e3cdc000e44f18e0f3a42ee0f041c412d36aaf5a4b52dddb0acc71ff3da0", "generation_seconds_batch": 15.577773706056178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.03645658493042, "target_z": -0.7460937454423513, "ce": 6.300607204437256, "genuineness": 4.068024158477783, "identity": 0.40939635038375854, "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/vn_VOLT_reg_high/ec0e943297ee7a23d1fcbb9cb60c9196b0d2bbd0140a91981b99eefbc80a1986.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "ec1541d2c15377a3617207a1e9a9d55dc57a0625f80b49cba5c487e89c2384d0", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "22383183f3712838b7eaa9f32544cc234dad5b1e82f526c87083af1c1df2c20b", "generation_seconds_batch": 14.850619941949844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3003038167953491, "target_z": -1.5937499378014996, "ce": 6.308549880981445, "genuineness": 4.055472373962402, "identity": 0.4606790542602539, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ec1541d2c15377a3617207a1e9a9d55dc57a0625f80b49cba5c487e89c2384d0.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": "ec40154a7db32007ff2a8582940c98ddbec889cf86ceaef15c846c40e5fccead", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "27798c491557d70db90967d93b00626b70f85ec725457c959fd0f0ee7bfd3e9a", "generation_seconds_batch": 15.382084197015502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.948253870010376, "target_z": -0.8476563296248042, "ce": 6.078212261199951, "genuineness": 4.168440818786621, "identity": 0.6175606846809387, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ec40154a7db32007ff2a8582940c98ddbec889cf86ceaef15c846c40e5fccead.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "ecab9c26c09030eb14ed0c7a0e72f488e756abd16287135e0939de17539c3e0f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5742cf4dd0858f837dd8d3a39f4ecb67dd7d67204a208d775d3988b006ea1c7d", "generation_seconds_batch": 22.60227452800609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5649117231369019, "target_z": -1.2890624597854523, "ce": 6.260893821716309, "genuineness": 4.494794845581055, "identity": 0.6557239294052124, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ecab9c26c09030eb14ed0c7a0e72f488e756abd16287135e0939de17539c3e0f.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": "ed32e92fe2257ff07366455b1554f03f9ee328035e651b1633d85f585d9bd2ef", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d104e2628c1d425a30ce7e57927d3e5d62dbb5497fe224afc1b9a83a15eb0c19", "generation_seconds_batch": 20.920846708933823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.246785879135132, "target_z": -0.5039063403486836, "ce": 6.229123115539551, "genuineness": 4.218649387359619, "identity": 0.25572797656059265, "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/vn_VOLT_reg_high/ed32e92fe2257ff07366455b1554f03f9ee328035e651b1633d85f585d9bd2ef.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "ed87d5b6c4761d6a590b4999318e64fa75115a6b1731411b864f43dede429e30", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b22f10c3f18713d49fead23060b059435ffe47f4b21579ad4447b748e12bdf42", "generation_seconds_batch": 21.507710578036495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6124054193496704, "target_z": -1.234374998927612, "ce": 6.0305562019348145, "genuineness": 3.9801597595214844, "identity": 0.6180449724197388, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ed87d5b6c4761d6a590b4999318e64fa75115a6b1731411b864f43dede429e30.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": "ede1e67816040cd05da9327e61ec369216c4e275551b60731e2185fdbd08ebb2", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e28ff348571a86905ad0a9e68c4c663bfb30bfc70530f2f4ed1ecad97012d0a", "generation_seconds_batch": 15.10900234093424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.097519874572754, "target_z": -0.6757813349867439, "ce": 6.2767791748046875, "genuineness": 4.243753433227539, "identity": 0.6997791528701782, "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/vn_VOLT_reg_high/ede1e67816040cd05da9327e61ec369216c4e275551b60731e2185fdbd08ebb2.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "ede8d32492ef8189e376bd188ba18877c8dcd98d33ed8f0ed4395da16b192ba5", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "329051504d42baaf5613d7c2de6ea64aa463fac599ee754824d5017ffa48097c", "generation_seconds_batch": 16.03875931398943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.625039577484131, "target_z": -0.06835939470512832, "ce": 5.752562999725342, "genuineness": 3.6475296020507812, "identity": 0.5596047043800354, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ede8d32492ef8189e376bd188ba18877c8dcd98d33ed8f0ed4395da16b192ba5.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "ee1f1b05605374d61947ac5bd7a085c680db0819c9242ff8a49f43fef97f9460", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fde64097b4535e7ce7b734366fdd9278a43c3a19288ddd67d4b62bddc0897283", "generation_seconds_batch": 20.61471846397035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5258116722106934, "target_z": -0.18261713032831817, "ce": 6.09409761428833, "genuineness": 3.998987913131714, "identity": 0.5124697685241699, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ee1f1b05605374d61947ac5bd7a085c680db0819c9242ff8a49f43fef97f9460.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "ee25b4cfed1cd5616037eef1a32abe98ac09f37d9164046faca4a4c29864fed7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "40ffce47093a4905245ae1fa0d63012db7ad3860023619e6f636421500affdf9", "generation_seconds_batch": 21.669427786022425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8498740196228027, "target_z": -0.9609375573727545, "ce": 6.149696350097656, "genuineness": 3.8922953605651855, "identity": 0.4273078739643097, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ee25b4cfed1cd5616037eef1a32abe98ac09f37d9164046faca4a4c29864fed7.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "eeea8d07c63e619e69eff6d22515a01555cf181a1c26bfa1ca1e16be5a2d4021", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8fed440a702c8281fc415297b8b71ef57a17f1b905d2b3a3dc29ff8a3fae41c1", "generation_seconds_batch": 21.665578585932963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.265444278717041, "target_z": -0.48242179443685634, "ce": 6.133810997009277, "genuineness": 4.300237655639648, "identity": 0.5083641409873962, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/eeea8d07c63e619e69eff6d22515a01555cf181a1c26bfa1ca1e16be5a2d4021.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "ef098f0e03fc31cd490eb0a75d827f213f211e78f15558f2b1e7e4ef7f5053cc", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "005fa77f65e43a41a0e70a710d4d6189287e41098abb6e0fce4f5013e05b0f75", "generation_seconds_batch": 21.315544163924642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.490278720855713, "target_z": -1.3749999571044826, "ce": 6.443574905395508, "genuineness": 4.1998209953308105, "identity": 0.518778920173645, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ef098f0e03fc31cd490eb0a75d827f213f211e78f15558f2b1e7e4ef7f5053cc.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "ef14e04be933eff0e733304a940bd233cc406a048f079f658e9f8f220c412326", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "afa196c2573934904d2255a1510e9a301a4e3bf1942d908c6c789ab394bed0bd", "generation_seconds_batch": 22.309263046015985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9448615312576294, "target_z": -0.8515624983914181, "ce": 5.9431867599487305, "genuineness": 4.13078498840332, "identity": 0.4007217586040497, "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/vn_VOLT_reg_high/ef14e04be933eff0e733304a940bd233cc406a048f079f658e9f8f220c412326.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "ef537735b77dc1dc710b0ef0dfeb4da6e0948b09936dd21379a56497240db5da", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7ea5e115794b826da4617499af07c4a1ae95ae45429c59c69f45db6d6a2f8c20", "generation_seconds_batch": 20.51092041202355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6962802410125732, "target_z": 0.013671933847287977, "ce": 5.895530700683594, "genuineness": 3.8420867919921875, "identity": 0.26723647117614746, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ef537735b77dc1dc710b0ef0dfeb4da6e0948b09936dd21379a56497240db5da.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "ef5eecaad7d61c0a2359c1d79f663ec5ebd1d02634de735d928defebb85411a4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "490eaae7a237bee81999eb75c5c2eaee905b2908526e6ffd4011f1e0add46099", "generation_seconds_batch": 21.342964345938526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2460252046585083, "target_z": -1.6562500107238793, "ce": 6.221180438995361, "genuineness": 4.319066047668457, "identity": 0.4863358438014984, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ef5eecaad7d61c0a2359c1d79f663ec5ebd1d02634de735d928defebb85411a4.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "efa419d7e060b4cbe56cef3c1d1247ef8bd627fe1e105fa4980260e152a7f9dd", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P03", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Speak with a clear intention toward one unheard listener standing nearby.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bd88361f18aeb3abd5f59d5e4c66a48688cec378f0cde01e1e8bfb0460f946a0", "generation_seconds_batch": 16.06618768395856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3138734102249146, "target_z": -1.5781249882037327, "ce": 5.903473377227783, "genuineness": 4.061748504638672, "identity": 0.6940499544143677, "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/vn_VOLT_reg_high/efa419d7e060b4cbe56cef3c1d1247ef8bd627fe1e105fa4980260e152a7f9dd.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "f00deba710f7d9b37281247785a2d6d2d8b4ca8caeb00dd0ef70d18ab89fd60c", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9b8f1cd0bb2fe92ba0992c929a23ffa5608eba9ce0530da65865f48d6c3a21f6", "generation_seconds_batch": 14.931279892916791, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8532664775848389, "target_z": -0.957031251340485, "ce": 6.252951145172119, "genuineness": 4.381826400756836, "identity": 0.26348382234573364, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f00deba710f7d9b37281247785a2d6d2d8b4ca8caeb00dd0ef70d18ab89fd60c.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "f0443edbcf691c3ae3b559d180745f2e91ce95df75acb738df97cf7d88bc414d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3e9a798cf5491175bc5700ecff9a06f09978f9b642bf3c0fd4ca5b43b5ea9cab", "generation_seconds_batch": 21.993132918025367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4834939241409302, "target_z": -1.3828124319033661, "ce": 6.046441555023193, "genuineness": 4.319066047668457, "identity": 0.6649830341339111, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f0443edbcf691c3ae3b559d180745f2e91ce95df75acb738df97cf7d88bc414d.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "f09ca32aceb382a17531903851a306b9532c23ba49caa83481971f6df32b250d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d06ff6c5302889f47649cfc94f85da05c8d16ca5aab2688a3001ae05358623d2", "generation_seconds_batch": 20.30744131805841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.559648275375366, "target_z": 1.0078124061660556, "ce": 5.069493293762207, "genuineness": 3.9048471450805664, "identity": 0.35690903663635254, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble ce qu'elle continue.", "wer": 0.21052631578947367, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f09ca32aceb382a17531903851a306b9532c23ba49caa83481971f6df32b250d.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "f137cc6f4ad166a08261423ec1c41ca1bcab2110c7a0680509c112c36dbfb804", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "abfa93feb738c917cf86d59d86cd4bbd6c9f12d778ad1b1d2d9c6b4ad7013327", "generation_seconds_batch": 15.623937548953108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.982177972793579, "target_z": -0.8085938183647309, "ce": 6.109982967376709, "genuineness": 4.093128204345703, "identity": 0.46587830781936646, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinaus.", "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/vn_VOLT_reg_high/f137cc6f4ad166a08261423ec1c41ca1bcab2110c7a0680509c112c36dbfb804.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "f1ad9e663e52e01ab388ffc90353184938d0b5a73bf8d1da52e50efa2f52dd6e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "57695399715d7b9289d3a2cc07cc7afe6d6e6f80adb414ce4676e2221e387ce5", "generation_seconds_batch": 21.1457587829791, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5784813165664673, "target_z": -1.2734375101876854, "ce": 6.213237762451172, "genuineness": 4.293961524963379, "identity": 0.32468199729919434, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f1ad9e663e52e01ab388ffc90353184938d0b5a73bf8d1da52e50efa2f52dd6e.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "f1af37e860d2c4775f3b64ddabce6adcc0d6bda4b1441f9856e719308e6c8d7e", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P07", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. React naturally to a silent partner and keep one consistent adult voice.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ddd4c1176a81e3aea6a4c0051e3b268128a2598302cff2f7ee5706cf5d5b62f0", "generation_seconds_batch": 16.162707755924203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6124054193496704, "target_z": -1.234374998927612, "ce": 6.372091293334961, "genuineness": 4.532451152801514, "identity": 0.3629037141799927, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f1af37e860d2c4775f3b64ddabce6adcc0d6bda4b1441f9856e719308e6c8d7e.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "f1d07197730dbd6e8bfadcac7d2780bbe9d8370fe2d2c06a8a9893d97bf17e73", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4aa290c33bb94d2c60748b73363cef6587cb60813659ba6cc9ffc3f16bdbea33", "generation_seconds_batch": 14.566136463079602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1374680995941162, "target_z": -1.7812500193029828, "ce": 6.133810997009277, "genuineness": 3.9676074981689453, "identity": 0.7248786091804504, "hypothesis": "La porte 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/vn_VOLT_reg_high/f1d07197730dbd6e8bfadcac7d2780bbe9d8370fe2d2c06a8a9893d97bf17e73.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": "f20c83cc4e46b4bb8b47e6d9068b19a668dfd866cccdd2b521e1fd1ecf789fac", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [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": "d3795d6d7c8203525a234b33f3118c7ca863b1f3c652c7b29ee4e2742e24c56d", "generation_seconds_batch": 13.83209074207116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9584312438964844, "target_z": -0.8359374115279953, "ce": 6.141753673553467, "genuineness": 4.444586753845215, "identity": 0.7683708667755127, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien and verify the two dernier chiffres. Appelle moi quand tu auras un moment.", "wer": 0.22727272727272727, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f20c83cc4e46b4bb8b47e6d9068b19a668dfd866cccdd2b521e1fd1ecf789fac.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "f215acd0849acb157ce55a25f505a0e7887eaf6a8e1eb03c9a0988e3a756fe68", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3f72f61dd4f69772b2df57e1f60e7b03a6d7d41be0cea58bd60484881a2a1f5", "generation_seconds_batch": 20.190976098063402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.768456220626831, "target_z": -1.0546875294906681, "ce": 5.720792293548584, "genuineness": 4.061748504638672, "identity": 0.6609470248222351, "hypothesis": "La porte 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/vn_VOLT_reg_high/f215acd0849acb157ce55a25f505a0e7887eaf6a8e1eb03c9a0988e3a756fe68.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "6b5419a64861c73215a2759dd95289c852f2186de6ebc06c06469865511cb603", "generation_seconds_batch": 17.536195621010847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.436000108718872, "target_z": -1.437500030026862, "ce": 6.24500846862793, "genuineness": 4.413206577301025, "identity": 0.759547233581543, "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/vn_VOLT_reg_high/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.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": "f2d9783a6968d2a696d78192b8237690fbe513eb7f5f2ab66bc8a2e04f6d603a", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Escribí el número en el sobre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "f19f464ba97def1ef3d6d46d688fa15cee99556a5d563f1495b90ac45e3f18af", "generation_seconds_batch": 20.529932930949144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8329119682312012, "target_z": -0.9804688130027912, "ce": 6.0305562019348145, "genuineness": 4.080576419830322, "identity": 0.6416068077087402, "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": 0.120000000000001, "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/vn_VOLT_reg_high/f2d9783a6968d2a696d78192b8237690fbe513eb7f5f2ab66bc8a2e04f6d603a.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "f330725f20acec7ed8a1b348b21a7ee06aa507d2e7dc3c744d77fd04f9b4be0e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] The door is still open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] I put your coat on the chair.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3677e2b3775e63e635d1c82aee1fca53d151512530f046490a1b0fd5358ce23b", "generation_seconds_batch": 19.82143739599269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7302043437957764, "target_z": 0.052734445107361305, "ce": 6.173524379730225, "genuineness": 3.8044304847717285, "identity": 0.47591841220855713, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f330725f20acec7ed8a1b348b21a7ee06aa507d2e7dc3c744d77fd04f9b4be0e.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "f4187f282fc7638a1cdf10a68be52133b1cad086e05542de345937b49b8b459f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "96ce3c7b7f068074508fac4c09073b7f966b79c34465b9525b95eee7d3ac2922", "generation_seconds_batch": 16.044967207941227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4224305152893066, "target_z": -1.4531249796246293, "ce": 6.070269584655762, "genuineness": 4.607763767242432, "identity": 0.5671812295913696, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f4187f282fc7638a1cdf10a68be52133b1cad086e05542de345937b49b8b459f.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": "f47b77e220c78f9b4824c2cdf34fbe74eab15df516906aaf6881aced4d2d537b", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b83d1c33abc7f3e38219b164649f4978217b6d79f22721a3fb906ef0bb803352", "generation_seconds_batch": 13.549068054999225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.811622142791748, "target_z": 0.14648441722527497, "ce": 6.252951145172119, "genuineness": 3.9801597595214844, "identity": 0.4475374221801758, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f47b77e220c78f9b4824c2cdf34fbe74eab15df516906aaf6881aced4d2d537b.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "f5dea6508b2644efa9a993feb5aac4f762cb1dbbacfbe4873c1ff88e0f40412f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c0fa3c5132963c56d01cf29ef73cbc142fd7b01aec316082e2bbbf523c814108", "generation_seconds_batch": 14.80027357803192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4893431663513184, "target_z": -0.22460943974542164, "ce": 5.796247482299805, "genuineness": 4.042920112609863, "identity": 0.5745890140533447, "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/vn_VOLT_reg_high/f5dea6508b2644efa9a993feb5aac4f762cb1dbbacfbe4873c1ff88e0f40412f.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "f61294d3871f9ca4719a3b967f9567b41628544074f0fb7f2736362a28b5f49e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c6a51521151e494442a8a5b2353b0071598d36586379ef0301685631332d834b", "generation_seconds_batch": 19.566090628039092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7209625244140625, "target_z": -1.1093749903485086, "ce": 6.340320587158203, "genuineness": 4.068024158477783, "identity": 0.6154621839523315, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f61294d3871f9ca4719a3b967f9567b41628544074f0fb7f2736362a28b5f49e.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "f66d834114d757cda9b9a5b7a946f3418cb580752e4c4295112174491a7986cb", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c0f8805ba94881ea9fd8e5ed56431db29018adea74f1afa8536b2469157e2eb1", "generation_seconds_batch": 20.489748116931878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.476709008216858, "target_z": -1.3906250439679053, "ce": 6.419747352600098, "genuineness": 4.093128204345703, "identity": 0.390142023563385, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f66d834114d757cda9b9a5b7a946f3418cb580752e4c4295112174491a7986cb.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "f68e6f6507f480a304c12c1e6fd220e411dd8acf40a8e05ae66d62be0b3c4941", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "932e163feef1395f745eb14d50cefb364e19d8bf46166004fb40520dbfebb812", "generation_seconds_batch": 21.37348916591145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.046633720397949, "target_z": -0.734375101876854, "ce": 6.23706579208374, "genuineness": 4.061748504638672, "identity": 0.42952555418014526, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f68e6f6507f480a304c12c1e6fd220e411dd8acf40a8e05ae66d62be0b3c4941.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "f6efab8c198919d3439696c69c27a910c7b07c89e1b479e4a03ded733640bb54", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "49118f4305b3141ac3dde93100b55b5901e8f4fabdfc934cd72d8318e2945944", "generation_seconds_batch": 14.874036789056845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5581269264221191, "target_z": -1.296874934584336, "ce": 5.935244083404541, "genuineness": 4.143336772918701, "identity": 0.51642906665802, "hypothesis": "He encontrado. La cajita estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f6efab8c198919d3439696c69c27a910c7b07c89e1b479e4a03ded733640bb54.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "f73bb243c06a32485737024d5a43868889b23888275055c8075d71044f862d65", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b406c8bca372d0186160ed6cc7db2fa6951ad41ec11ca1087a092c8c4a0563c3", "generation_seconds_batch": 20.533020277041942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7209625244140625, "target_z": -1.1093749903485086, "ce": 6.141753673553467, "genuineness": 4.419482707977295, "identity": 0.5820950269699097, "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/vn_VOLT_reg_high/f73bb243c06a32485737024d5a43868889b23888275055c8075d71044f862d65.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "f73c9d2b61d8d1bb964003cfac792c108235bbc6988b50834c9be6d5d364619e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e48f8b5cc0e8d3436face539e761ea0c267e7781c86e85ced023d439e2bf6b95", "generation_seconds_batch": 21.047867411980405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.476709008216858, "target_z": -1.3906250439679053, "ce": 5.998785495758057, "genuineness": 4.174716949462891, "identity": 0.6337237358093262, "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/vn_VOLT_reg_high/f73c9d2b61d8d1bb964003cfac792c108235bbc6988b50834c9be6d5d364619e.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "464ab09cb0fc0d1dceae09e6d253cf0f24002d6d277f99950db05a6bff0d707f", "generation_seconds_batch": 16.459339090040885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4563546180725098, "target_z": -1.414062468364556, "ce": 6.09409761428833, "genuineness": 4.545003414154053, "identity": 0.7738023400306702, "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/vn_VOLT_reg_high/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "f831d461a12e0da2aedc790201e64bc1d565f44a67d8b7acc3d6096d91570129", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7d8c6cbc1723fa87081b4dbbda85759156529bf3cdc2d3a9fff50f6d5ecdb7c", "generation_seconds_batch": 14.673926985939033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.063595771789551, "target_z": -0.7148438462468173, "ce": 6.070269584655762, "genuineness": 3.9550557136535645, "identity": 0.6572895646095276, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f831d461a12e0da2aedc790201e64bc1d565f44a67d8b7acc3d6096d91570129.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": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": "60a80af760ac463919cab9827d9d51208936f96c7aa43c480f90506c90bcd408", "generation_seconds_batch": 14.992098537040874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.415645718574524, "target_z": -1.4609374544235127, "ce": 6.252951145172119, "genuineness": 4.444586753845215, "identity": 0.5999353528022766, "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/vn_VOLT_reg_high/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "f8a3345cf75f536106ef37d6853fa2edbe88a889aa91828d8a143d72e7f6b19a", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P05", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Establish the delivery, sustain it through the middle thought and release it at the end.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7dcf60a34ed57ae7a71bed4775237c04b9fca70f09db2c99cb35a254df6c9e85", "generation_seconds_batch": 15.567576886969618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4292153120040894, "target_z": -1.4453125048257458, "ce": 6.070269584655762, "genuineness": 4.6203155517578125, "identity": 0.623116672039032, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f8a3345cf75f536106ef37d6853fa2edbe88a889aa91828d8a143d72e7f6b19a.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "f9735474df68758ff70426bfee1b3d058ce8defe793f808de06e6557230a3fbc", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8dc7302702afe39a284429b7c2a8fde2ccafd877a1e1140c212239a988ba40e5", "generation_seconds_batch": 17.007827472058125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5935723781585693, "target_z": 1.046874917426129, "ce": 5.629451274871826, "genuineness": 4.042920112609863, "identity": 0.6756272315979004, "hypothesis": "La porte 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/vn_VOLT_reg_high/f9735474df68758ff70426bfee1b3d058ce8defe793f808de06e6557230a3fbc.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "f985c5110cce2164801d9fd162c7b802f971a7181f9146eca3e627f8778d55ab", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c066e99139390aa9c355f62272336684c173d7afef5463b9b6285c8bbbdef00c", "generation_seconds_batch": 20.665254767984152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8065335750579834, "target_z": 0.1406250954425263, "ce": 5.307773113250732, "genuineness": 3.6914620399475098, "identity": 0.44918328523635864, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lento.", "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/vn_VOLT_reg_high/f985c5110cce2164801d9fd162c7b802f971a7181f9146eca3e627f8778d55ab.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "f9fb6773e329090e71c463ae949221b89ac1b2eefa50287894549a71b12089d7", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bcf92ed4615effa141f4ff56dfeb8bb182af336dffed91b9fcae38609dd898f7", "generation_seconds_batch": 21.629279676941223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3070886135101318, "target_z": -1.5859374630026162, "ce": 6.054384231567383, "genuineness": 4.055472373962402, "identity": 0.6954615116119385, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/f9fb6773e329090e71c463ae949221b89ac1b2eefa50287894549a71b12089d7.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "fa00b62b62ff17100157648bad46a35970a51208bea061c31db1981f21b10980", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Tür ist noch offen.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b456d5e0b8c9d6959275e70eabd234060054905ff33e4748bd9621e006960cf7", "generation_seconds_batch": 21.190412599011324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7209625244140625, "target_z": -1.1093749903485086, "ce": 6.292664527893066, "genuineness": 4.293961524963379, "identity": 0.5621760487556458, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fa00b62b62ff17100157648bad46a35970a51208bea061c31db1981f21b10980.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": "fa363d23a8ddbff86cc4f5f8fa5ac99ad87a3636ea0908fdf7b7f1e349c655ce", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f32f8b7e9fcc85c0e8bb87c3d2a70f3fe81c53172c69b3ae556adf475bbc84d", "generation_seconds_batch": 22.275628053001128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1280517578125, "target_z": -0.6406248552276287, "ce": 6.070269584655762, "genuineness": 4.086852550506592, "identity": 0.5593124032020569, "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/vn_VOLT_reg_high/fa363d23a8ddbff86cc4f5f8fa5ac99ad87a3636ea0908fdf7b7f1e349c655ce.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "fa4526d472d025787437a1f8073eb1e4596b94424629d4833e32ec4053ec4b10", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1dca4c29f1f18f4b71e7fbe8fb9998bfd4e84f47b16fcbb4d4902075bb87329f", "generation_seconds_batch": 20.792780348914675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.808229684829712, "target_z": 0.1425781111930053, "ce": 6.157639026641846, "genuineness": 4.243753433227539, "identity": 0.6055797338485718, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble ce qu'elle a.", "wer": 0.21052631578947367, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fa4526d472d025787437a1f8073eb1e4596b94424629d4833e32ec4053ec4b10.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "fa68f10c3b53d3b949b95d7c61996cbde0e3da7eaaf9ea3e740db1a46210838b", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P09", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Follow the local performance direction beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e3c6dad5c95d7475464d5c7915976b30c748847b26312d9462c7636c81a705e", "generation_seconds_batch": 15.93534588906914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.476709008216858, "target_z": -1.3906250439679053, "ce": 6.070269584655762, "genuineness": 4.306513786315918, "identity": 0.6279365420341492, "hypothesis": "La porte 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/vn_VOLT_reg_high/fa68f10c3b53d3b949b95d7c61996cbde0e3da7eaaf9ea3e740db1a46210838b.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "fa7890bff06f0f615828ec5e0e073e75bad8735b1da8285e7ed9efab52fb724f", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a847d205c16d186c55aa0d97de525908058bd4e58ce5b7cedd01d23e9f4263cc", "generation_seconds_batch": 21.76834372803569, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.155190944671631, "target_z": -0.6093749560320947, "ce": 6.157639026641846, "genuineness": 3.9425034523010254, "identity": 0.31676071882247925, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschreiten.", "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/vn_VOLT_reg_high/fa7890bff06f0f615828ec5e0e073e75bad8735b1da8285e7ed9efab52fb724f.mp3" }, { "id": "vn_VOLT_reg_high-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-0", "key": "fab13f4a9d6492fa63e3bef6b018eda6948ae9919b5d56e8e63f6a2db55b8909", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "de6b210084d8e243fe615aeff49672d644c237f01066e857a4abd907cfd1778c", "generation_seconds_batch": 15.587706797989085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5513420104980469, "target_z": -1.3046875466488752, "ce": 6.284721851348877, "genuineness": 4.042920112609863, "identity": 0.49185025691986084, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fab13f4a9d6492fa63e3bef6b018eda6948ae9919b5d56e8e63f6a2db55b8909.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": "fb61894ea6fc4f794ec80faf47df0e99a0c391b35e6a229bf92920813d89558b", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c624b6bcd24834e208e82a8fd1d7585f12ab6becfe326e4fcc370e585e03207", "generation_seconds_batch": 22.275628053001128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1382288932800293, "target_z": -0.6289062116621313, "ce": 6.1020402908325195, "genuineness": 4.231201171875, "identity": 0.506989061832428, "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/vn_VOLT_reg_high/fb61894ea6fc4f794ec80faf47df0e99a0c391b35e6a229bf92920813d89558b.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "fb695f9e9fadb60bd0810c8664a71048dd7b6be049346c97c4fcec1826d3e3bf", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "939806f8751471f80ed8beefa45a175307ef3b9bfea92754873d840403bd65e8", "generation_seconds_batch": 20.796252400963567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.811622142791748, "target_z": 0.14648441722527497, "ce": 6.046441555023193, "genuineness": 3.9801597595214844, "identity": 0.4858381450176239, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fb695f9e9fadb60bd0810c8664a71048dd7b6be049346c97c4fcec1826d3e3bf.mp3" }, { "id": "vn_VOLT_reg_high-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-0", "key": "fc27505fc1f9da612a00b89f01c1936c6850234f5db260feec35fe40918728bd", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] De deur staat nog open.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f48acc8490dd009d8827dd29cfaa8aaca03d69989fd5d2a0bafcb186a6b861a2", "generation_seconds_batch": 20.524754739017226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2950403690338135, "target_z": 0.7031249281500083, "ce": 5.919358730316162, "genuineness": 3.415316104888916, "identity": 0.29869943857192993, "hypothesis": "De deur 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/vn_VOLT_reg_high/fc27505fc1f9da612a00b89f01c1936c6850234f5db260feec35fe40918728bd.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "fc33d9832acf4a06343e6ffc62327c32a7fce3a6745713c85aedf4ea5fe7eeda", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "6e245851f0f65b788ed3b2095826bf0c1b8192bd37f5fc59e21f04c968ab4f1b", "generation_seconds_batch": 21.840540231089108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3866355419158936, "target_z": 0.8085938183647309, "ce": 5.804190158843994, "genuineness": 3.848362922668457, "identity": 0.5651023387908936, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fc33d9832acf4a06343e6ffc62327c32a7fce3a6745713c85aedf4ea5fe7eeda.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "fc807dbdabb5b6b2fa4e50f50f561f1ebd68ecffd4e24fc79bc5638de8fdc799", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ba0ad00467b293bf6abf77c221b6255c044c42a14c765c612f0f39ef222b9064", "generation_seconds_batch": 22.309263046015985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.218885898590088, "target_z": -1.6875000471850692, "ce": 6.0305562019348145, "genuineness": 3.8671910762786865, "identity": 0.6636204123497009, "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/vn_VOLT_reg_high/fc807dbdabb5b6b2fa4e50f50f561f1ebd68ecffd4e24fc79bc5638de8fdc799.mp3" }, { "id": "vn_VOLT_reg_high-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-0", "key": "fd0d220c16a91ba0c9a3323546403d76f4fa5abc2d3ae7d917b56d74f509c166", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "355503707035906daa5dcba973a545f3279aba0a01f6a56f4899b8282b67b18b", "generation_seconds_batch": 19.859023174038157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1374680995941162, "target_z": -1.7812500193029828, "ce": 5.796247482299805, "genuineness": 3.613011360168457, "identity": 0.3771814703941345, "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/vn_VOLT_reg_high/fd0d220c16a91ba0c9a3323546403d76f4fa5abc2d3ae7d917b56d74f509c166.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": "fd2b358f84ee8530c832cc546620cc3ea16d8fb48ee1e58b61361ed1c78179ec", "bucket": "vn_VOLT_reg_high", "phase": "heldout", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "917295669e616035cfc796e5324a8b9a1c9a96fe72ac5bd61d2cb652dd896a6a", "generation_seconds_batch": 21.604011559975334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.463900089263916, "target_z": -0.2539063231904766, "ce": 6.1894097328186035, "genuineness": 4.105680465698242, "identity": 0.4099496603012085, "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": 0.120000000000001, "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/vn_VOLT_reg_high/fd2b358f84ee8530c832cc546620cc3ea16d8fb48ee1e58b61361ed1c78179ec.mp3" }, { "id": "vn_VOLT_reg_high-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-es-1", "key": "fd46633635052f8aa43820bf435950dd1bbb5de3af7e6727898e6289abf79c46", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "01ae82b62551e912c05f5661a9ded301211a376f21ca6a8d91cdb3e6ac9f4daf", "generation_seconds_batch": 14.91561769193504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.490278720855713, "target_z": -1.3749999571044826, "ce": 6.09409761428833, "genuineness": 4.68307638168335, "identity": 0.7081848382949829, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fd46633635052f8aa43820bf435950dd1bbb5de3af7e6727898e6289abf79c46.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "fd47e46a180499a0769e91dc6f5ff95c46e03f4a8dc96cb49deec17295253674", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "543f76abc00d69151ea0ce310ddedc072f43b806762e3fb715ae9825e4bf931c", "generation_seconds_batch": 20.174441277049482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1491668224334717, "target_z": 0.5351562395442176, "ce": 5.863759994506836, "genuineness": 3.660081624984741, "identity": 0.5478295683860779, "hypothesis": "Ik 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/vn_VOLT_reg_high/fd47e46a180499a0769e91dc6f5ff95c46e03f4a8dc96cb49deec17295253674.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "fd4847b1e32b95dd48f90ccf68bbfa5c54ecbe9a3cd2fc9c2521b7599d208f8e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78f4e935887d6c60f73da20fcd1ad07a51306a1dd8a12da244fcd3801368dddc", "generation_seconds_batch": 20.819428190006875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9557995796203613, "target_z": 0.3125000900805866, "ce": 5.561938762664795, "genuineness": 4.017816066741943, "identity": 0.464259535074234, "hypothesis": "La porte 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/vn_VOLT_reg_high/fd4847b1e32b95dd48f90ccf68bbfa5c54ecbe9a3cd2fc9c2521b7599d208f8e.mp3" }, { "id": "vn_VOLT_reg_high-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-1", "key": "fd9c70e5c29e226ca191876e56434cc2b382d4c0da4daa9de61dd6d15a74393e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "60984d89103b75593a6d31ead83b9dfa0bb33fb391d58195257d999e3b0652ef", "generation_seconds_batch": 21.568163929972798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.341012716293335, "target_z": -1.5468749517425429, "ce": 6.117925643920898, "genuineness": 4.419482707977295, "identity": 0.6397812366485596, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fd9c70e5c29e226ca191876e56434cc2b382d4c0da4daa9de61dd6d15a74393e.mp3" }, { "id": "vn_VOLT_reg_high-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-0", "key": "fde7cdf3434ce06384a19c6b686aa79432d11c3dc5e26ae8e8ba459420cdf3ed", "bucket": "vn_VOLT_reg_high", "phase": "wording", "candidate": "canonical-extension-P08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Carry the delivery through the global direction.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9c792c0ae067512d6c2766e9ed005ba7e6a3033da30ceb0f0cda4f9b44a42377", "generation_seconds_batch": 15.396183019969612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.205295085906982, "genuineness": 4.344170093536377, "identity": 0.5894525647163391, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fde7cdf3434ce06384a19c6b686aa79432d11c3dc5e26ae8e8ba459420cdf3ed.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "fe1607261a7b22d9209408c4625b31f32e7a4925cb426633b94456b45fa0375d", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "07596b4d6e59950899601cce4f09093ed03dd076ce55e6ecd606231c71b558db", "generation_seconds_batch": 22.09997738606762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.03645658493042, "target_z": -0.7460937454423513, "ce": 6.149696350097656, "genuineness": 3.848362922668457, "identity": 0.33891305327415466, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinaus.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fe1607261a7b22d9209408c4625b31f32e7a4925cb426633b94456b45fa0375d.mp3" }, { "id": "vn_VOLT_reg_high-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-fr-0", "key": "fe47f2a5d7fa772dc140895e1efd714d72ad92b09fc6b2662a93d3cdaa348c63", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] La porte est encore ouverte.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e307456763ec563f20b38f7411dc0a4418b8a054bbdacc5ab9ac7038005d7204", "generation_seconds_batch": 21.456864006002434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.068509578704834, "target_z": 1.593749800535844, "ce": 5.792276382446289, "genuineness": 3.8295347690582275, "identity": 0.8115839958190918, "hypothesis": "La porte est encore ouverte. J'ai poussé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fe47f2a5d7fa772dc140895e1efd714d72ad92b09fc6b2662a93d3cdaa348c63.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "fe87232e7a979f499b8d1dab702f85b81b68af704190fd1ea286fc387f3625b4", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1b455d4b76a91d1970534458b3c9ae6d35d87762e51cf7afa619e4a9035c095d", "generation_seconds_batch": 14.458082851022482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8532664775848389, "target_z": -0.957031251340485, "ce": 6.205295085906982, "genuineness": 4.105680465698242, "identity": 0.6017597317695618, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fe87232e7a979f499b8d1dab702f85b81b68af704190fd1ea286fc387f3625b4.mp3" }, { "id": "vn_VOLT_reg_high-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-nl-1", "key": "febf969d06e487bbf4832dc53b2c742c203ef986bdf883742e1b555dea27b8d1", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Het stond naast het oude raam.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "093078367f7c36b2ccca062b6c637649c60697c3ea980bcf4ac6b74083529743", "generation_seconds_batch": 21.117394782952033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.464660882949829, "target_z": 0.898437484450375, "ce": 5.720792293548584, "genuineness": 3.653805732727051, "identity": 0.3072810769081116, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/febf969d06e487bbf4832dc53b2c742c203ef986bdf883742e1b555dea27b8d1.mp3" }, { "id": "vn_VOLT_reg_high-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-de-1", "key": "ff620c1e35bf819291516c8537b0b39c5c8d824d40019e14812667143adfd12e", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "16773154e8a594edb026bc53aae884ef7a1f84cd6a7403676d28c9c14b913d00", "generation_seconds_batch": 21.05031862691976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.436000108718872, "target_z": -1.437500030026862, "ce": 6.2767791748046875, "genuineness": 4.105680465698242, "identity": 0.3005514144897461, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/ff620c1e35bf819291516c8537b0b39c5c8d824d40019e14812667143adfd12e.mp3" }, { "id": "vn_VOLT_reg_high-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "vn_VOLT_reg_high-en-1", "key": "fffcbd7390e72e1651f1491cfa03d8060f589c0b11928708a094bcde8c608f5b", "bucket": "vn_VOLT_reg_high", "phase": "grid", "candidate": "canonical-extension-P01", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.\nSCRIPT:\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] I found the little box.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.8 seconds duration] It was beside the old window.\n(Emotionally volatile delivery with abrupt changes of attitude, pitch energy and emotional control across the connected thoughts. Make this audible from the opening words and keep every word clear.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "545776e9aad01601b7e0d835055bfa37cfbf96d9756a12b1e2d2de977faf0809", "generation_seconds_batch": 14.475291953072883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7980525493621826, "target_z": 0.13085946762750794, "ce": 6.006728172302246, "genuineness": 4.18099308013916, "identity": 0.6425459980964661, "hypothesis": "I f found the little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_VOLT_reg_high/fffcbd7390e72e1651f1491cfa03d8060f589c0b11928708a094bcde8c608f5b.mp3" }, { "key": "original-vn_VOLT_reg_high-de-0-seed1701-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "3ec90f79ca6ae1a96462b126ed8181f1580ce4e0d0d9872a638021eb24fb29f8", "task_id": "vn_VOLT_reg_high-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.173524379730225, "genuineness": 4.15588903427124, "identity": 0.5507258772850037, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/b54da6633715f264f85273d3.mp3" }, { "key": "original-vn_VOLT_reg_high-de-0-seed1701-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "3a96d6aeb5b1e7340e4f331eea116eeb1918f58d2b78dca62368ee5d45ff8d4e", "task_id": "vn_VOLT_reg_high-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.6191902160644531, "target_z": -1.2265625241287286, "ce": 6.23706579208374, "genuineness": 4.419482707977295, "identity": 0.6076068878173828, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/52744332f9b6560353ba07b2.mp3" }, { "key": "original-vn_VOLT_reg_high-de-0-seed1701-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "ae080eb3d31b1bb409e4bf0e8543d2a6ab22eb7372bbab7f66c9e0d410eef10b", "task_id": "vn_VOLT_reg_high-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.6463295221328735, "target_z": -1.1953124876675387, "ce": 6.205295085906982, "genuineness": 4.356721878051758, "identity": 0.6223178505897522, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/3fc550c7851c9f7263aa9f04.mp3" }, { "key": "original-vn_VOLT_reg_high-de-0-seed1701-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "f0e57142a55f633dbf4c5ae78ffe3695ce931f85586a17879bddc8ed81d53f12", "task_id": "vn_VOLT_reg_high-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.436000108718872, "target_z": -1.437500030026862, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.5362110137939453, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/9e1ff985d3ce16f9a4e77ffa.mp3" }, { "key": "original-vn_VOLT_reg_high-de-0-seed1702-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "b96cf3ab50fc63e2e253ddcc11f2edd2310b2003746125996d39cc1961147fff", "task_id": "vn_VOLT_reg_high-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.4292153120040894, "target_z": -1.4453125048257458, "ce": 6.205295085906982, "genuineness": 4.507347106933594, "identity": 0.5533186197280884, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/27d9a63730e8e5f04df34db1.mp3" }, { "key": "original-vn_VOLT_reg_high-de-0-seed1702-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "5c212595c4dcc5898b5ebd1c033797bd06a5df5b277f08e3163b5564a8fe4ce1", "task_id": "vn_VOLT_reg_high-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.5649117231369019, "target_z": -1.2890624597854523, "ce": 6.229123115539551, "genuineness": 4.319066047668457, "identity": 0.7068386077880859, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/2de21d6e920c3e0991feebb3.mp3" }, { "key": "original-vn_VOLT_reg_high-de-0-seed1702-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "12ef26dd51a1a02fc44d1ca6db026e1ab36ec1778a23f95154458daa07286288", "task_id": "vn_VOLT_reg_high-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.7413170337677002, "target_z": -1.0859374286862022, "ce": 6.213237762451172, "genuineness": 4.532451152801514, "identity": 0.5187942981719971, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/5b4c8358858f80a8fd5ad645.mp3" }, { "key": "original-vn_VOLT_reg_high-de-0-seed1702-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "acc413c13ddee6c0a3ec7de4e9c58147778c3eae8a0be945b4359e8bd7e5700c", "task_id": "vn_VOLT_reg_high-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.7820258140563965, "target_z": -1.0390625798929012, "ce": 6.117925643920898, "genuineness": 4.469690799713135, "identity": 0.3790607154369354, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/e3a2f768fd7da805fd21e772.mp3" }, { "key": "original-vn_VOLT_reg_high-de-1-seed1701-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "d046b5c0ebc6618534e68abc5e3a0205c7513e85cd763d1e99a9fc636c182905", "task_id": "vn_VOLT_reg_high-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.2867341041564941, "target_z": -1.6093750246649225, "ce": 6.356205940246582, "genuineness": 4.118232727050781, "identity": 0.5063896775245667, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/dec3371e1bc79dfd1e25810d.mp3" }, { "key": "original-vn_VOLT_reg_high-de-1-seed1701-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "e28f03d9bbcbed64e40048797ba1f738ec04a61579081f7e1ee637e083c7223a", "task_id": "vn_VOLT_reg_high-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3817216157913208, "target_z": -1.499999965683586, "ce": 6.332377910614014, "genuineness": 4.325342178344727, "identity": 0.5067606568336487, "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/audio/vn_VOLT_reg_high/de/591ec4cadd034d6ba8fe9154.mp3" }, { "key": "original-vn_VOLT_reg_high-de-1-seed1701-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "fd1cba695e2f26a2560a20e1022d1daba4d6afc1b057e24c508f14344cee9449", "task_id": "vn_VOLT_reg_high-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.4427849054336548, "target_z": -1.4296875552279786, "ce": 6.427689552307129, "genuineness": 4.287685871124268, "identity": 0.5862481594085693, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/d0a8b32ca0338bf5d471e0ad.mp3" }, { "key": "original-vn_VOLT_reg_high-de-1-seed1701-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "619ec573661e6fb454991a74e65c51594e1d0177e202ed135aede3977cd3b02c", "task_id": "vn_VOLT_reg_high-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.2324556112289429, "target_z": -1.6718749603216463, "ce": 6.284721851348877, "genuineness": 4.444586753845215, "identity": 0.5964559316635132, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/7ded56ed8f0a5e43c5c9a6ec.mp3" }, { "key": "original-vn_VOLT_reg_high-de-1-seed1702-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "35b4306747fe74131e2197b59a8269ba9d81aa8f35b1dc43850d2e3ab45f5f9b", "task_id": "vn_VOLT_reg_high-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.4970635175704956, "target_z": -1.3671874823055992, "ce": 6.443574905395508, "genuineness": 4.319066047668457, "identity": 0.4703294038772583, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/f5331fdfc8c5757279ca8bb8.mp3" }, { "key": "original-vn_VOLT_reg_high-de-1-seed1702-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "b49c5c21fa264f64b6d45a7f4b4bb65fa749dd8545e188521eb3ea1d23b47b9c", "task_id": "vn_VOLT_reg_high-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3885064125061035, "target_z": -1.4921874908847026, "ce": 6.395919322967529, "genuineness": 4.331617832183838, "identity": 0.47460561990737915, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/d3a3997423f67bcb4a2e9925.mp3" }, { "key": "original-vn_VOLT_reg_high-de-1-seed1702-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "c91d1431a2c63ab77e6d264467c86114808d74577221a13a8bd1f18f0fd719f0", "task_id": "vn_VOLT_reg_high-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.5174179077148438, "target_z": -1.3437500579089485, "ce": 6.292664527893066, "genuineness": 4.381826400756836, "identity": 0.3035883903503418, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/81822170f6c8fd43e538dcfd.mp3" }, { "key": "original-vn_VOLT_reg_high-de-1-seed1702-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "db0b5d5abb6f7b04ac9494f1e6db0b08f9a98869e8b281d1cc118f1302d8c000", "task_id": "vn_VOLT_reg_high-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.348263263702393, "genuineness": 4.293961524963379, "identity": 0.5069552063941956, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/de/b9feca00e1a6ae23f29c4fd5.mp3" }, { "key": "original-vn_VOLT_reg_high-en-0-seed1701-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "96bb4b89ab1afc7736ae6fd3dd796b2de9c035881be1836068647e91b4346b5f", "task_id": "vn_VOLT_reg_high-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3206582069396973, "target_z": -1.5703125134048492, "ce": 6.173524379730225, "genuineness": 4.143336772918701, "identity": 0.3928425908088684, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/32ae1de079bec8df35630a59.mp3" }, { "key": "original-vn_VOLT_reg_high-en-0-seed1701-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "f1b68fae8ec82a28eadb40019a2a0f2bf1ff7d9b192386215427b6056577f42e", "task_id": "vn_VOLT_reg_high-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.6666839122772217, "target_z": -1.1718750632708883, "ce": 6.141753673553467, "genuineness": 4.124508857727051, "identity": 0.4793899357318878, "hypothesis": "The 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/vn_VOLT_reg_high/en/a30ec885ff577ec0557334c0.mp3" }, { "key": "original-vn_VOLT_reg_high-en-0-seed1701-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "e3b41d7b349579a6833942c127da691fd4578f5bff452d8a29f6a0f353a6a0d4", "task_id": "vn_VOLT_reg_high-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.8532664775848389, "target_z": -0.957031251340485, "ce": 6.141753673553467, "genuineness": 4.174716949462891, "identity": 0.3791945278644562, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/28f1f96fd37d9623fc4d8ea4.mp3" }, { "key": "original-vn_VOLT_reg_high-en-0-seed1701-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "06d025cb942cd9c6a75b8f8fca4894e58d219f78371f7f40d7bf3696a3dcc693", "task_id": "vn_VOLT_reg_high-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.5445572137832642, "target_z": -1.3125000214477587, "ce": 6.213237762451172, "genuineness": 3.9048471450805664, "identity": 0.2654179632663727, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/41147019a0642036a35a9c7f.mp3" }, { "key": "original-vn_VOLT_reg_high-en-0-seed1702-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "a02dead505702fc45c56c1875a785f2092d25ecab54c44effe0b650d7a621f13", "task_id": "vn_VOLT_reg_high-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.4834939241409302, "target_z": -1.3828124319033661, "ce": 6.213237762451172, "genuineness": 4.105680465698242, "identity": 0.22028064727783203, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/fdcdf9135722b8e4f7bbafbc.mp3" }, { "key": "original-vn_VOLT_reg_high-en-0-seed1702-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "8dc5dea261a63884d665fc48539218caaaf47ba8312e08b06142148927e583db", "task_id": "vn_VOLT_reg_high-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3477975130081177, "target_z": -1.5390624769436594, "ce": 6.173524379730225, "genuineness": 3.9550557136535645, "identity": 0.23293237388134003, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/70c6cc40786347464187b10c.mp3" }, { "key": "original-vn_VOLT_reg_high-en-0-seed1702-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "c90c5452b88cb668b24f6ce0a26ddd3b508bfd0d28e3c14a4f6743996b46542d", "task_id": "vn_VOLT_reg_high-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3545823097229004, "target_z": -1.531250002144776, "ce": 6.125868320465088, "genuineness": 3.8797430992126465, "identity": 0.41623765230178833, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/03724af899a96f23cfa69c2f.mp3" }, { "key": "original-vn_VOLT_reg_high-en-0-seed1702-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "5d947971e177611986ca67eae3a5ebcc861d1b9fdfb4ac96b4d6185dd4244be5", "task_id": "vn_VOLT_reg_high-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.6191902160644531, "target_z": -1.2265625241287286, "ce": 6.221180438995361, "genuineness": 4.20609712600708, "identity": 0.30192068219184875, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/f651b6d0057acedf8efe08a5.mp3" }, { "key": "original-vn_VOLT_reg_high-en-1-seed1701-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "03e8c7e8a7ac757dfa479056845eb5476e496eaa005725797534e018894d66df", "task_id": "vn_VOLT_reg_high-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5445572137832642, "target_z": -1.3125000214477587, "ce": 6.435632705688477, "genuineness": 4.595211505889893, "identity": 0.5687420964241028, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/e6876856e1e2e7572da42845.mp3" }, { "key": "original-vn_VOLT_reg_high-en-1-seed1701-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "553836214da1851b54f5b22f5654050bc6558658aa95ed6b1347ff3c1923b1c2", "task_id": "vn_VOLT_reg_high-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.476709008216858, "target_z": -1.3906250439679053, "ce": 6.23706579208374, "genuineness": 4.419482707977295, "identity": 0.4782618284225464, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/4d33b2186a78febcfe3839f1.mp3" }, { "key": "original-vn_VOLT_reg_high-en-1-seed1701-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "2ad9563ae1bad8485b58a913e702aba721f50e54e0976f331cff500565380379", "task_id": "vn_VOLT_reg_high-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5174179077148438, "target_z": -1.3437500579089485, "ce": 6.229123115539551, "genuineness": 4.068024158477783, "identity": 0.533516526222229, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/8fce67a6e3e887b0c3469805.mp3" }, { "key": "original-vn_VOLT_reg_high-en-1-seed1701-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "90187c6be375effc5587fb2a3dbf7a8452041d98eeb78f2c5a1ec08d23303a66", "task_id": "vn_VOLT_reg_high-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8532664775848389, "target_z": -0.957031251340485, "ce": 6.252951145172119, "genuineness": 4.250029563903809, "identity": 0.5270382761955261, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/f31b3fc22d474cd87fe8bb76.mp3" }, { "key": "original-vn_VOLT_reg_high-en-1-seed1702-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "6b5c8b04d84aa59209de5eea7f1828cd3420c81676fb038d92449438c1252829", "task_id": "vn_VOLT_reg_high-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5649117231369019, "target_z": -1.2890624597854523, "ce": 6.284721851348877, "genuineness": 4.193545341491699, "identity": 0.24823206663131714, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/65dbd05b8b7a4354789c5605.mp3" }, { "key": "original-vn_VOLT_reg_high-en-1-seed1702-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "139168a87505bf8c02d5aa200cc7cbfedb5bc2f6423f8a284772e1c4aa5fa51d", "task_id": "vn_VOLT_reg_high-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2731645107269287, "target_z": -1.6249999742626895, "ce": 6.395919322967529, "genuineness": 4.15588903427124, "identity": 0.3202219307422638, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/7c03f9655aa16767d939df24.mp3" }, { "key": "original-vn_VOLT_reg_high-en-1-seed1702-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "7d32a1ad8871b7be217ac6e06c11895ffe2737915586af8e8deae5a867c316c3", "task_id": "vn_VOLT_reg_high-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8227348327636719, "target_z": -0.9921874565682886, "ce": 6.3641486167907715, "genuineness": 4.413206577301025, "identity": 0.5191992521286011, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/840291205f4cc562d9506c18.mp3" }, { "key": "original-vn_VOLT_reg_high-en-1-seed1702-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "eda0f7c5836c3530ff685bc3b5b84da10d8e68f8bd2b793cad44dc76ade3a460", "task_id": "vn_VOLT_reg_high-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6463295221328735, "target_z": -1.1953124876675387, "ce": 6.2767791748046875, "genuineness": 4.381826400756836, "identity": 0.4601372182369232, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/en/ffccfc87c8f80beb4afd8882.mp3" }, { "key": "original-vn_VOLT_reg_high-es-0-seed1701-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "930bc75ed9b219ef11d27b7af609a4cb2360ebec447219be5a5671bf01410a55", "task_id": "vn_VOLT_reg_high-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.252810001373291, "target_z": -1.6484375359249959, "ce": 6.133810997009277, "genuineness": 4.293961524963379, "identity": 0.3308109641075134, "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/vn_VOLT_reg_high/es/5fce05d4a0d200dd341f707c.mp3" }, { "key": "original-vn_VOLT_reg_high-es-0-seed1701-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "1b0173219568d142429df7e57d74d2296046abbe041e297d1aa1b95e46313d1c", "task_id": "vn_VOLT_reg_high-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.4563546180725098, "target_z": -1.414062468364556, "ce": 6.141753673553467, "genuineness": 4.20609712600708, "identity": 0.6279064416885376, "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/vn_VOLT_reg_high/es/4d3ed26268cc5669f530bb9d.mp3" }, { "key": "original-vn_VOLT_reg_high-es-0-seed1701-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "9605382677b9b8e428862afb042878769c948f486db8f8c19c51f50336acba3f", "task_id": "vn_VOLT_reg_high-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.2731645107269287, "target_z": -1.6249999742626895, "ce": 5.967014789581299, "genuineness": 3.8922953605651855, "identity": 0.5509543418884277, "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/vn_VOLT_reg_high/es/416fc72590566e56b3049668.mp3" }, { "key": "original-vn_VOLT_reg_high-es-0-seed1701-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "57f20c26d80b68b0e7d36bc08a70157766565bcd627a117fa97758026bb0ed6c", "task_id": "vn_VOLT_reg_high-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3817216157913208, "target_z": -1.499999965683586, "ce": 5.998785495758057, "genuineness": 4.168440818786621, "identity": 0.656456708908081, "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/vn_VOLT_reg_high/es/3c10e78cd59dda826c481b8a.mp3" }, { "key": "original-vn_VOLT_reg_high-es-0-seed1702-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "2a5573d4f511cd209865cb4f6b6b7d0891fef282e69abc7b02589606a8c2d70d", "task_id": "vn_VOLT_reg_high-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.6191902160644531, "target_z": -1.2265625241287286, "ce": 5.77639102935791, "genuineness": 4.356721878051758, "identity": 0.5942311882972717, "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/vn_VOLT_reg_high/es/d4770f43deaf7f080577afb9.mp3" }, { "key": "original-vn_VOLT_reg_high-es-0-seed1702-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "0ae1b0b232f9523c99a10dba936e2c806c269918599f92d3632702bad1c75104", "task_id": "vn_VOLT_reg_high-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3885064125061035, "target_z": -1.4921874908847026, "ce": 6.054384231567383, "genuineness": 4.080576419830322, "identity": 0.6085845232009888, "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/vn_VOLT_reg_high/es/11a610f84de7f63109c88177.mp3" }, { "key": "original-vn_VOLT_reg_high-es-0-seed1702-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "223918027d6b9e9f2a50d512f615106327686d732f21463bd6418693ad10762c", "task_id": "vn_VOLT_reg_high-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 5.967014789581299, "genuineness": 4.18099308013916, "identity": 0.4821295440196991, "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/vn_VOLT_reg_high/es/06dd42355c57641a690c4c09.mp3" }, { "key": "original-vn_VOLT_reg_high-es-0-seed1702-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "63b02acd38f2c534a564bdc25611bbb54570b53116415c7bce59f587c8402224", "task_id": "vn_VOLT_reg_high-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.2799493074417114, "target_z": -1.617187499463806, "ce": 6.022613525390625, "genuineness": 4.143336772918701, "identity": 0.48124411702156067, "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/vn_VOLT_reg_high/es/39599f6b4e831888626f5873.mp3" }, { "key": "original-vn_VOLT_reg_high-es-1-seed1701-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "d5e96ba30b5a3d88a38997a4da2363fd79fb8c9f960dd944587619af8b4f7da0", "task_id": "vn_VOLT_reg_high-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3342278003692627, "target_z": -1.5546875638070823, "ce": 6.125868320465088, "genuineness": 4.419482707977295, "identity": 0.7812811136245728, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/es/6e02e31fed5f49a3ad83afe2.mp3" }, { "key": "original-vn_VOLT_reg_high-es-1-seed1701-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "ec83d1539134b7b45de843d65a6c4b9d401f171b6f6e0db122be8435e01b97a8", "task_id": "vn_VOLT_reg_high-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.7616714239120483, "target_z": -1.0625000042895518, "ce": 6.300607204437256, "genuineness": 4.770940780639648, "identity": 0.503738522529602, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/es/b0f6eebe15d8736e8a83fa31.mp3" }, { "key": "original-vn_VOLT_reg_high-es-1-seed1701-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "450befc6ca7cf8050c237653ce6f006699520dcf57787e4f66b274d67075c364", "task_id": "vn_VOLT_reg_high-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.4834939241409302, "target_z": -1.3828124319033661, "ce": 6.1894097328186035, "genuineness": 4.570107460021973, "identity": 0.4229457676410675, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/es/04573785ff0b47f6bec843ac.mp3" }, { "key": "original-vn_VOLT_reg_high-es-1-seed1701-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "bbdf23328d614053bdf15d0e031e064851e2efb43ddae7737b0a06c0223bf5be", "task_id": "vn_VOLT_reg_high-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.7006080150604248, "target_z": -1.132812552010815, "ce": 6.292664527893066, "genuineness": 4.68307638168335, "identity": 0.6284093856811523, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/es/e36b4c7e402d8c1442da5ef6.mp3" }, { "key": "original-vn_VOLT_reg_high-es-1-seed1702-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "9ccd5dba74732f24bb1375b36d128cbbe2e9a03700c4b37ae3dbaf906c66bdc9", "task_id": "vn_VOLT_reg_high-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.5377724170684814, "target_z": -1.3203124962466422, "ce": 6.268836498260498, "genuineness": 4.7332844734191895, "identity": 0.5602139830589294, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/es/e506fd4b1e4d6fe6467ab1ee.mp3" }, { "key": "original-vn_VOLT_reg_high-es-1-seed1702-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "7c6936def4d3eef1ac6656f08abee6f0508cc30441c9ae4972b998039714d2d8", "task_id": "vn_VOLT_reg_high-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.2867341041564941, "target_z": -1.6093750246649225, "ce": 6.09409761428833, "genuineness": 4.425758361816406, "identity": 0.7451200485229492, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/es/93e2077c87fdbee8067cd1ef.mp3" }, { "key": "original-vn_VOLT_reg_high-es-1-seed1702-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "fd0a90ea937c55a3401767de5351a88d8d9aee24d964bab89367c0390764e28e", "task_id": "vn_VOLT_reg_high-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.8023803234100342, "target_z": -1.0156250182305948, "ce": 6.117925643920898, "genuineness": 4.582659721374512, "identity": 0.679042398929596, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/es/0591522f0ee6707602b3fe2c.mp3" }, { "key": "original-vn_VOLT_reg_high-es-1-seed1702-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "1132700e12263e19b80ee2f381682ea2775dd0be4278a4396d702b22a79adb3e", "task_id": "vn_VOLT_reg_high-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.58526611328125, "target_z": -1.2656250353888019, "ce": 6.173524379730225, "genuineness": 4.519899368286133, "identity": 0.5830245614051819, "hypothesis": "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/vn_VOLT_reg_high/es/0fdffd795a7c69670d59c4a1.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-0-seed1701-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "6cf11534381c3205e3f9a2144e5fb44db9356c86f0afe5424e7ce695173434a1", "task_id": "vn_VOLT_reg_high-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3003038167953491, "target_z": -1.5937499378014996, "ce": 6.181467056274414, "genuineness": 4.256305694580078, "identity": 0.8029129505157471, "hypothesis": "La porte 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/vn_VOLT_reg_high/fr/39fc630dd862340ddc6034dc.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-0-seed1701-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "f30a2de8b7757cc0ff0d51f4a95df2d5d1080ee84c41a3aa34b65e6af93a471e", "task_id": "vn_VOLT_reg_high-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3206582069396973, "target_z": -1.5703125134048492, "ce": 6.149696350097656, "genuineness": 4.507347106933594, "identity": 0.8058298230171204, "hypothesis": "La porte 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/audio/vn_VOLT_reg_high/fr/212f1a4d8b83ac607d5d1e28.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-0-seed1701-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "bfdc0223386e62a463e9451190cd01e657e3ef9a02fb300683eb13a18427c38f", "task_id": "vn_VOLT_reg_high-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.9075450897216797, "target_z": -0.8945311784181053, "ce": 6.157639026641846, "genuineness": 4.532451152801514, "identity": 0.7290262579917908, "hypothesis": "La porte 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/vn_VOLT_reg_high/fr/191c9e8ce2efec1617ddd147.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-0-seed1701-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "f2cccf4a28dd21afeb1e37862566b85899a78934e305e06552bda811b889dd1b", "task_id": "vn_VOLT_reg_high-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.3138734102249146, "target_z": -1.5781249882037327, "ce": 6.006728172302246, "genuineness": 4.306513786315918, "identity": 0.676478922367096, "hypothesis": "La porte 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/vn_VOLT_reg_high/fr/56f4a5f86afdbadad9169c4f.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-0-seed1702-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "66ac8f6618fb3630d95ad96e5d09dc28c5464adac5b21eef0c46fc0c1fdd5ce0", "task_id": "vn_VOLT_reg_high-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.2731645107269287, "target_z": -1.6249999742626895, "ce": 6.1894097328186035, "genuineness": 4.243753433227539, "identity": 0.7998070120811462, "hypothesis": "La porte 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/vn_VOLT_reg_high/fr/25af6d4d429fdc4b1e6ca8c4.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-0-seed1702-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "11b4526336061a00837298b240fa718215fb9fefab0c9bdc0a6606b8088b3699", "task_id": "vn_VOLT_reg_high-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.4224305152893066, "target_z": -1.4531249796246293, "ce": 6.086154937744141, "genuineness": 4.432034492492676, "identity": 0.5869359970092773, "hypothesis": "La porte 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/vn_VOLT_reg_high/fr/6eb3536da48b43354bde10d9.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-0-seed1702-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "14697fcedd33b08797f05232cc151346fbec313a829adeb41853d92d6465c789", "task_id": "vn_VOLT_reg_high-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.2121011018753052, "target_z": -1.6953125219839527, "ce": 5.895530700683594, "genuineness": 4.080576419830322, "identity": 0.8166594505310059, "hypothesis": "La porte 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/vn_VOLT_reg_high/fr/950dfda0fa58772a6e28506e.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-0-seed1702-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "4cb694b8e7b0d3d91ac0cf37580789cb9cda16c607eb7fba5321fef4eacd46bd", "task_id": "vn_VOLT_reg_high-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.103543996810913, "target_z": -1.820312530563056, "ce": 6.062326908111572, "genuineness": 4.042920112609863, "identity": 0.5873538851737976, "hypothesis": "La porte 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/vn_VOLT_reg_high/fr/ac1d496da497ef43a5a9263e.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-1-seed1701-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "b28cab38cc66baaeb7a67b6c0afe64d93376cd16a14d9579faa6d42285c55ee8", "task_id": "vn_VOLT_reg_high-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4224305152893066, "target_z": -1.4531249796246293, "ce": 6.205295085906982, "genuineness": 4.381826400756836, "identity": 0.681232213973999, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/fr/eb2859072dfcd6cd62b83897.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-1-seed1701-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "81c30ddb6531470f2dd1764c9c2b2a6b8f91b7d53c463574079f3829adeef3e2", "task_id": "vn_VOLT_reg_high-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4088608026504517, "target_z": -1.468750066488052, "ce": 6.109982967376709, "genuineness": 4.595211505889893, "identity": 0.8090664148330688, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/fr/b76e090d3bfdd8e098efd2ca.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-1-seed1701-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "984581452a85e60c9017a96c48358c72cd0e43546f9a3dadd9aa1a70e4c06d4f", "task_id": "vn_VOLT_reg_high-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5716965198516846, "target_z": -1.2812499849865688, "ce": 6.165581703186035, "genuineness": 4.607763767242432, "identity": 0.6499708890914917, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/fr/338f14ac479c7d3b219bb656.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-1-seed1701-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "4f7f322daa20f787f560f459e02fa9a51fe398d6b53fcd6a5bed6e16221bfdca", "task_id": "vn_VOLT_reg_high-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.252810001373291, "target_z": -1.6484375359249959, "ce": 5.982900142669678, "genuineness": 4.469690799713135, "identity": 0.7258083820343018, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/fr/da1c24b5784f76230cce55c1.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-1-seed1702-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "ce772c0c0dda84246ca31da4800a3a263b0d80b581eb4d3b7a32384cfb5075be", "task_id": "vn_VOLT_reg_high-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5716965198516846, "target_z": -1.2812499849865688, "ce": 6.197352409362793, "genuineness": 4.570107460021973, "identity": 0.729620099067688, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/fr/e6f89ee23ef791a1d319146e.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-1-seed1702-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "8b8c183dc41ea79388ce354e0ff09b7cf35c2af9a3b491fe6d88f81c2e591761", "task_id": "vn_VOLT_reg_high-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449569821357727, "target_z": -1.4218749431634394, "ce": 6.1894097328186035, "genuineness": 4.432034492492676, "identity": 0.7092874050140381, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/fr/762dbf724f18bf242c3287d2.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-1-seed1702-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "b3dd72e5029ea147af73413f105a53ad639f12593f3066c09b6f90bd5b5d1896", "task_id": "vn_VOLT_reg_high-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5174179077148438, "target_z": -1.3437500579089485, "ce": 6.1020402908325195, "genuineness": 4.494794845581055, "identity": 0.6599699258804321, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/fr/e9418d0614ada30b669678f0.mp3" }, { "key": "original-vn_VOLT_reg_high-fr-1-seed1702-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "671bb1fc2f06e0db8697f62ec79244bb2953f822b13b3541477b47eec841ba49", "task_id": "vn_VOLT_reg_high-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5309876203536987, "target_z": -1.3281249710455256, "ce": 6.133810997009277, "genuineness": 4.6705241203308105, "identity": 0.7155344486236572, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/fr/8fd12c693cd16daa1921be70.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-0-seed1701-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "c9d4d505bbb9b7aeede530a64d96df0107036a83d93b3befcb5f3c1ac3da7290", "task_id": "vn_VOLT_reg_high-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.8770133256912231, "target_z": -0.9296875209115647, "ce": 6.252951145172119, "genuineness": 4.344170093536377, "identity": 0.7265163064002991, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/9b6ffc35845eff4df516b1a0.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-0-seed1701-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "26539983af2bd36a96bc0ac0c2c0dbdbf49646ee34d3ade4e2232b58d97d7d74", "task_id": "vn_VOLT_reg_high-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 2.0534186363220215, "target_z": -0.7265624898123146, "ce": 6.197352409362793, "genuineness": 4.20609712600708, "identity": 0.7308071255683899, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/c79265d7ac1ad382b265259f.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-0-seed1701-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "e259cf05110ed45e4d5a54dd31786d2af6defa80d0343d347f5596c8a1b4cd27", "task_id": "vn_VOLT_reg_high-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 2.19250750541687, "target_z": -0.5664061387397517, "ce": 6.133810997009277, "genuineness": 4.149612903594971, "identity": 0.757233202457428, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/567ecba9a18fbd852bbefd5d.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-0-seed1701-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "a9abbea6a93928e6a07d78cb284a3afcb1de8da4066f41a76bfef5f5c9d08923", "task_id": "vn_VOLT_reg_high-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.4631394147872925, "target_z": -1.4062499935656725, "ce": 6.086154937744141, "genuineness": 4.15588903427124, "identity": 0.587087869644165, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/33bef9407a279e0715663b24.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-0-seed1702-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "373e7f2c2dcfba3cb82a2471c90b21c0d4263c171286862b96ab4a6798bb6878", "task_id": "vn_VOLT_reg_high-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.510633111000061, "target_z": -1.351562532707832, "ce": 5.9431867599487305, "genuineness": 4.494794845581055, "identity": 0.526576578617096, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/e9738947fcb85d113bbfd186.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-0-seed1702-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "8b7b31687f057f6bd5c2b8c80d09b637fee6429b110473823b1688f32e07520f", "task_id": "vn_VOLT_reg_high-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.9686083793640137, "target_z": -0.8242187679624979, "ce": 6.09409761428833, "genuineness": 4.268857479095459, "identity": 0.5850460529327393, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/9b148ddc33a71766daa384ef.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-0-seed1702-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "dd74809dea3cf34548f9992d380c5ad4fba366ee3848bd705a5f57c4a055c932", "task_id": "vn_VOLT_reg_high-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 2.043241500854492, "target_z": -0.738281133377812, "ce": 6.062326908111572, "genuineness": 4.281409740447998, "identity": 0.654369056224823, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/08ac11103312fb558921cee6.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-0-seed1702-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "4ed11c901b28203b884172257fe0008999a92845c106df0426dbf99d32115748", "task_id": "vn_VOLT_reg_high-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.7006080150604248, "target_z": -1.132812552010815, "ce": 6.022613525390625, "genuineness": 4.15588903427124, "identity": 0.7812868356704712, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/82baf45e004e6169b1d9c861.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-1-seed1701-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "45a33d2fd8df27ed8c41764f3a455cc7f22fdfcd143ee7c8456e311c4ae0705b", "task_id": "vn_VOLT_reg_high-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.9312918186187744, "target_z": -0.8671875852548409, "ce": 6.356205940246582, "genuineness": 4.432034492492676, "identity": 0.8321855068206787, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/1e675ef47eacb12559680d57.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-1-seed1701-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "0017757ffdce585868cfc5b0711e8d4253ad819910493b4cd4d63bd218b0f107", "task_id": "vn_VOLT_reg_high-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.659899115562439, "target_z": -1.1796875380697718, "ce": 6.157639026641846, "genuineness": 4.18099308013916, "identity": 0.6857284307479858, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/0ceb06bbe8a12d13f63b10ae.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-1-seed1701-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "a3826923bfc1f599e29ad8c54fdc428d4d2a6d05749144fe8552f1868493d2a9", "task_id": "vn_VOLT_reg_high-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.6124054193496704, "target_z": -1.234374998927612, "ce": 6.070269584655762, "genuineness": 4.055472373962402, "identity": 0.7705193758010864, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/4f62f187f8317fd5c44fdd4e.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-1-seed1701-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": 129, "seconds_generated": 10.32, "ended": true, "contract_sha256": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "6ffa33e7a356059c85b437ae697db43f85ac6d98f8248986e3162f6356740bed", "task_id": "vn_VOLT_reg_high-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.4631394147872925, "target_z": -1.4062499935656725, "ce": 6.165581703186035, "genuineness": 4.319066047668457, "identity": 0.7259376049041748, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/19329cb245aaee45a06f6755.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-1-seed1702-scale0.0", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "638899cd74573f4953dc2096eb898f62ff5777a212246fc41385c6b2da116fb3", "task_id": "vn_VOLT_reg_high-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.9414691925048828, "target_z": -0.8554686671580319, "ce": 6.062326908111572, "genuineness": 4.469690799713135, "identity": 0.6627804040908813, "hypothesis": "Ik heb een klein doosje 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/audio/vn_VOLT_reg_high/nl/4c5d59c2952c4707dac6d518.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-1-seed1702-scale0.5", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "67074200caa7e1fdbc1aa6d5eeb2902da85447999021912ded60f4b72d84b36f", "task_id": "vn_VOLT_reg_high-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.2799493074417114, "target_z": -1.617187499463806, "ce": 6.09409761428833, "genuineness": 4.168440818786621, "identity": 0.7190186381340027, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/b1381f427cd36956a624a2e8.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-1-seed1702-scale0.75", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "a963ba1265638058ecc984095bc1db8c7c16ce24ae353663487ee9020e548e99", "task_id": "vn_VOLT_reg_high-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.5309876203536987, "target_z": -1.3281249710455256, "ce": 5.9431867599487305, "genuineness": 4.243753433227539, "identity": 0.6249816417694092, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/eaaa8fcd39b62e4c900c7849.mp3" }, { "key": "original-vn_VOLT_reg_high-nl-1-seed1702-scale1.0", "bucket": "vn_VOLT_reg_high", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": [ "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "27de10b3a075e8008487e5abb5d58257e55c0803c855c3e8e9b525baa55fcc39", "mp3_sha256": "fd777e941a257ef67776f76ae0f87e57b43bdc71faaf69b23fb5b343f545168b", "task_id": "vn_VOLT_reg_high-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Emotionally volatile delivery with rapid or abrupt changes. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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(Emotionally volatile delivery with rapid or abrupt changes. 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": 1.218885898590088, "target_z": -1.6875000471850692, "ce": 6.229123115539551, "genuineness": 4.331617832183838, "identity": 0.6006255149841309, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_VOLT_reg_high/nl/4d14c3c5553d69d90b0765f5.mp3" } ], "source_standard_audio_unchanged": true }