{ "complete": true, "report": { "bucket": "emo_Interest", "label": "Intense Interest", "definition": { "id": "emo_Interest", "category": "emotion", "head": "emo_Interest", "pole": "high", "label": "Intense Interest", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_interest/full-v2-sealed/sealed-selected", "mission": "emotion_interest", "format_status": "CANONICAL", "heldout": true, "qualified": true, "source_cfg": 3, "source_model": { "label": "Humaneness 1.5 + real-speech rank 4", "repo": "laion/Humaneness-Voice-Large-1.5-RealSpeech-LoRAs", "revision": "fed33e554f094fcdc89fc0124aed2f9d42018714", "rank": 4 }, "metrics": { "ce": 6.288137168884277, "genuineness": 4.132541992664337, "wer": 0.011034899819174012, "identity": 0.5696953379362821, "voiceclap": 0.014212570860981941, "fitness": 0.7582496711728969, "steering_v2": 0.8739638320197349, "raw_target": 2.620151940584183, "target_cdf": 0.8739638320197349, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.293141040802002, "genuineness": 4.062626910209656, "wer": 0.009680842132455035, "identity": 0.5696953379362821, "fitness": 0.7545405927928795, "steering_v2": 0.8697090604548275 }, "none": { "n": 50, "ce": 6.283133296966553, "genuineness": 4.2024570751190184, "wer": 0.01238895750589299, "identity": null, "fitness": 0.7619587495529142, "steering_v2": 0.8782186035846423 } } } } ], "selected_wording": { "id": "manual-bb77d46f4025", "general": "Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.", "inline": [ "Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.", "Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.", "Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder." ], "cfg": 3, "recipe": "P06", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 1.3480468770631564, "target_raw": 2.6742658615112305, "ce": 6.162603211402893, "genuineness": 4.221159660816193, "identity": 0.5109773516654968, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.02951323091983795, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 1.2716796505796906, "target_raw": 2.6044586896896362, "ce": 6.133215308189392, "genuineness": 4.182562088966369, "identity": 0.5121693536639214, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.02832122892141342, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 1.3480468770631564, "target_raw": 2.6742658615112305, "ce": 6.162603211402893, "genuineness": 4.221159660816193, "identity": 0.5109773516654968, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.02951323091983795, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 1.2958007643308447, "target_raw": 2.626507765054703, "ce": 6.1624046802520756, "genuineness": 4.2268081426620485, "identity": 0.4917512772604823, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.04873930532485247, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 1.1402343592334103, "target_raw": 2.484304738044739, "ce": 6.173524379730225, "genuineness": 4.267602431774139, "identity": 0.4955673225224018, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.04492326006293297, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 0.9805664099878788, "target_raw": 2.3383524954319, "ce": 6.210060620307923, "genuineness": 4.285802912712097, "identity": 0.5437056303024292, "wer": 0.01067251461988304, "valid_fraction": 0.95, "identity_delta": 0.0032150477170944216, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 1.8925780852396668, "target_raw": 3.1720210552215575, "ce": 5.951725244522095, "genuineness": 4.105052924156189, "identity": 0.4041870338842273, "wer": 0.019122807017543857, "valid_fraction": 0.95, "identity_delta": -0.1363035487011075, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 1.6644531123408803, "target_raw": 2.9634923458099367, "ce": 6.033137655258178, "genuineness": 4.105680537223816, "identity": 0.4170311223715544, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.1234594602137804, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 1.4037108954345352, "target_raw": 2.7251482605934143, "ce": 6.093700504302978, "genuineness": 4.152437043190003, "identity": 0.4806737661361694, "wer": 0.03026315789473684, "valid_fraction": 0.95, "identity_delta": -0.059816816449165346, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 1.1320312578960303, "target_raw": 2.4768062949180605, "ce": 6.1977495670318605, "genuineness": 4.2657195091247555, "identity": 0.47957458421587945, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.06091599836945534, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 1.2716796505796906, "target_raw": 2.6044586896896362, "ce": 6.133215308189392, "genuineness": 4.182562088966369, "identity": 0.5121693536639214, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.02832122892141342, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 1.2537109443389811, "target_raw": 2.5880335211753844, "ce": 6.183849859237671, "genuineness": 4.22994612455368, "identity": 0.5027247063815594, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.0377658762037754, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 1.1685546760507561, "target_raw": 2.51019229888916, "ce": 6.16319887638092, "genuineness": 4.169696164131165, "identity": 0.49883962571620943, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.041650956869125365, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 1.139062484819245, "target_raw": 2.4832335293292997, "ce": 6.201323747634888, "genuineness": 4.28140959739685, "identity": 0.5104932084679603, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": -0.02999737411737442, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 1.1375000008150742, "target_raw": 2.4818052649497986, "ce": 6.229123067855835, "genuineness": 4.279213070869446, "identity": 0.5516602918505669, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.011169709265232086, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 1.135351576343524, "target_raw": 2.4798413932323458, "ce": 6.177495718002319, "genuineness": 4.261953997611999, "identity": 0.5052847437560558, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03520583882927895, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 1.1056640411934537, "target_raw": 2.452704060077667, "ce": 6.217209100723267, "genuineness": 4.277957916259766, "identity": 0.5330241918563843, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": -0.0074663907289505005, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 1.0619140587175468, "target_raw": 2.412712264060974, "ce": 6.204897952079773, "genuineness": 4.301806807518005, "identity": 0.5152436852455139, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.025246897339820863, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 1.02109376553735, "target_raw": 2.3753984928131104, "ce": 6.21939332485199, "genuineness": 4.296785962581635, "identity": 0.5135190263390541, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.02697155624628067, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 0.9623046683075521, "target_raw": 2.3216594636440275, "ce": 6.155851936340332, "genuineness": 4.261483299732208, "identity": 0.5612242549657822, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.020733672380447387, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 1.8281250250635286, "target_raw": 3.1131046056747436, "ce": 5.89275095462799, "genuineness": 4.070848572254181, "identity": 0.3907190585508943, "wer": 0.01609907120743034, "valid_fraction": 0.95, "identity_delta": -0.14977152403444052, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 1.7746093463959933, "target_raw": 3.0641860008239745, "ce": 5.83814504146576, "genuineness": 4.066769123077393, "identity": 0.40773828476667406, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.13275229781866074, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 1.7732421997897891, "target_raw": 3.0629362940788267, "ce": 5.848073410987854, "genuineness": 4.032564699649811, "identity": 0.3599023684859276, "wer": 0.0116593567251462, "valid_fraction": 1, "identity_delta": -0.1805882140994072, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 1.661718701757802, "target_raw": 2.9609928250312807, "ce": 5.996204209327698, "genuineness": 4.069279491901398, "identity": 0.3736941430717707, "wer": 0.011805555555555555, "valid_fraction": 1, "identity_delta": -0.1667964395135641, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 1.6349609276299621, "target_raw": 2.936533582210541, "ce": 5.978333163261413, "genuineness": 4.113839399814606, "identity": 0.42657985650002955, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.11391072608530521, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 1.5820312285533629, "target_raw": 2.88815062046051, "ce": 5.98905577659607, "genuineness": 4.145690298080444, "identity": 0.37745821066200735, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.16303237192332745, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 1.4953125414668946, "target_raw": 2.8088811933994293, "ce": 6.05359001159668, "genuineness": 4.133608889579773, "identity": 0.4058435572311282, "wer": 0.01111111111111111, "valid_fraction": 0.95, "identity_delta": -0.13464702535420656, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 1.4871094205677362, "target_raw": 2.8013827323913576, "ce": 6.063121223449707, "genuineness": 4.149769735336304, "identity": 0.4394798506051302, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.10101073198020458, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 1.485156242205854, "target_raw": 2.7995973348617555, "ce": 6.112961483001709, "genuineness": 4.187582850456238, "identity": 0.4694104723632336, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.07108011022210121, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 1.4791015718606166, "target_raw": 2.7940627694129945, "ce": 6.077815127372742, "genuineness": 4.151181876659393, "identity": 0.45518490597605704, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.08530567660927772, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.456054667084941, "target_raw": 2.772995626926422, "ce": 6.135399556159973, "genuineness": 4.189465677738189, "identity": 0.4563768610358238, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.08411372154951095, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.3822265463895511, "target_raw": 2.7055094480514525, "ce": 6.090523433685303, "genuineness": 4.1447489023208615, "identity": 0.4904292568564415, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.05006132572889328, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 1.2332031062278246, "target_raw": 2.5692873358726502, "ce": 6.128846836090088, "genuineness": 4.217707896232605, "identity": 0.48341958597302437, "wer": 0.016666666666666666, "valid_fraction": 0.95, "identity_delta": -0.05707099661231041, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 0.9037109149963136, "target_raw": 2.268098998069763, "ce": 6.176304316520691, "genuineness": 4.2199044823646545, "identity": 0.48328342102468014, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.05720716156065464, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": 0.7642578271076561, "target_raw": 2.1406251311302187, "ce": 6.200529456138611, "genuineness": 4.337894010543823, "identity": 0.5404905825853348, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.5, "n": 20, "target_z": 0.7295410174302618, "target_raw": 2.1088905453681948, "ce": 6.205295085906982, "genuineness": 4.302434360980987, "identity": 0.5518606066703796, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.011370024085044861, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": 0.822363285828424, "target_raw": 2.1937392473220827, "ce": 6.193381071090698, "genuineness": 4.310907065868378, "identity": 0.5803330406546593, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.039842458069324495, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": 0.7398437626845906, "target_raw": 2.1183082699775695, "ce": 6.225548887252808, "genuineness": 4.344170069694519, "identity": 0.5324693106114864, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.008021271973848342, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": 0.8261913928305691, "target_raw": 2.19723851442337, "ce": 6.286151475906372, "genuineness": 4.358855981826782, "identity": 0.5689422625303269, "wer": 0.01225108225108225, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 1.3906250125113875, "target_raw": 2.7131864738464357, "ce": 6.2127612018585205, "genuineness": 4.220155525207519, "identity": 0.5296556118130684, "wer": 0.013907961603613777, "valid_fraction": 0.98, "identity_delta": -0.03928665071725845, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 1.2596093812811648, "target_raw": 2.5934252738952637, "ce": 6.205453929901123, "genuineness": 4.235468997955322, "identity": 0.5183770287036896, "wer": 0.008203933747412007, "valid_fraction": 1, "identity_delta": -0.05056523382663727, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 1.2300781017041635, "target_raw": 2.5664307737350462, "ce": 6.241672506332398, "genuineness": 4.2950914478302, "identity": 0.5354235100746155, "wer": 0.0067186147186147184, "valid_fraction": 1, "identity_delta": -0.03351875245571136, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.029531279577001322, "ci95_z": [ -0.07640627179304368, 0.1670313012579723 ], "language_deltas": { "en": -0.1257812436322336, "de": -0.0640625288332462, "fr": 0.01640628092187361, "nl": 0.032031316581365356, "es": 0.28906257284724746 }, "languages_improved": 3, "clear_gain": false, "delta_ce": -0.036218576431274414, "delta_genuineness": -0.05962244987487793, "delta_wer": 0.0014853190287972893, "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": -0.13101563123022264, "ci95_z": [ -0.1989843915918521, -0.06140624799288004 ], "language_deltas": { "en": -0.2238281369968719, "de": -0.11210941241699528, "fr": -0.2113281345516496, "nl": -0.1132812411870113, "es": 0.005468769001414886 }, "languages_improved": 1, "clear_gain": false, "delta_ce": -0.0073072719573974605, "delta_genuineness": 0.015313472747802735, "delta_wer": -0.00570402785620177, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.5644336196808183, "ci95_z": [ 0.4817383091802969, 0.6571875314007296 ], "language_deltas": { "en": 0.5099609162189247, "de": 0.5425781863088548, "fr": 0.43134769763411374, "nl": 0.6046875367802187, "es": 0.7335937614619795 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.07339027404785156, "delta_genuineness": -0.1387004566192627, "delta_wer": 0.0016568793525315267, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 2.5, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793024126.2498448, "example": { "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [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.", "language": "nl", "seed": 1702, "scale": 0.0, "cfg": 2.5, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "0054a0530498c0647c5650794165bfdad164b86058811dc9ad367199bcbccf17", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a4e6430d4cd3a1ba9c447e26cb025ae24b86857ad15f8dee58bc1af05064cf8c", "generation_seconds_batch": 20.209325433941558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0416905879974365, "target_z": 1.7499999510955542, "ce": 6.062326908111572, "genuineness": 4.011539936065674, "identity": 0.5551974773406982, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0054a0530498c0647c5650794165bfdad164b86058811dc9ad367199bcbccf17.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "005bee184fa2a579c92df3f731f86c54eb4345c14467699668d472ed123535b5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "33957087b6464e7362ffa75d8d456d8f667efc8dd6cddbca2b516c2cab1bd575", "generation_seconds_batch": 20.49043053202331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5774998664855957, "target_z": 1.2421874006628444, "ce": 6.173524379730225, "genuineness": 4.231201171875, "identity": 0.3348788917064667, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/005bee184fa2a579c92df3f731f86c54eb4345c14467699668d472ed123535b5.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "00efd1e84a56016fb98152c59595fd7f18d30cd72faaeb555cf805aa7e46cc3d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f147342b7528213245e75eb8f8ba7777dbb79bb1673096714c4f760f042b584e", "generation_seconds_batch": 15.31947924697306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3987603187561035, "target_z": 2.140624929699859, "ce": 6.24500846862793, "genuineness": 4.168440818786621, "identity": 0.6359044313430786, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/00efd1e84a56016fb98152c59595fd7f18d30cd72faaeb555cf805aa7e46cc3d.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "0149e1978c4ee237b98e78d2fbe602ad751537a555438b6b74835f2c0917e845", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "05bf805cce8f42c01ac161c2dd6c79a41a843e8319f31975ebeb82cb4d57099e", "generation_seconds_batch": 23.12743502401281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.47752046585083, "target_z": 1.1328125422819688, "ce": 6.340320587158203, "genuineness": 4.507347106933594, "identity": 0.5684753060340881, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0149e1978c4ee237b98e78d2fbe602ad751537a555438b6b74835f2c0917e845.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "014fa27e6105f3baf369725fc12ad72f60640fba0113446b34779dcdc033ba99", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4fcf94cf24f5face8ac6e7a96defb4b559889bb844c05d083dc536787ac96051", "generation_seconds_batch": 15.900884718052112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3987603187561035, "target_z": 2.140624929699859, "ce": 6.229123115539551, "genuineness": 4.250029563903809, "identity": 0.48779749870300293, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/014fa27e6105f3baf369725fc12ad72f60640fba0113446b34779dcdc033ba99.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": "01e7a77a42cf6bfe7bb3f0f3a634bfddc0ada4c0c86bf67dfc139554278e540e", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d175ae55743c99229761eca689c7f645caa1b3c1e8f234cb97c98d8f3b001cfd", "generation_seconds_batch": 16.933233952964656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6132068634033203, "target_z": 1.281249924605646, "ce": 6.086154937744141, "genuineness": 4.413206577301025, "identity": 0.5861856937408447, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/01e7a77a42cf6bfe7bb3f0f3a634bfddc0ada4c0c86bf67dfc139554278e540e.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "01eeb50f4d311b1f93e394562b689b909cbd0ec14cc3f3b49fc5b482403063b4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a6958f2394d7981cd331bcf3265a67d23d3a1a896fae7ac26f40204c7d4a9b16", "generation_seconds_batch": 20.7917255529901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0488319396972656, "target_z": 1.7578124037193723, "ce": 6.117925643920898, "genuineness": 4.570107460021973, "identity": 0.3014912009239197, "hypothesis": "He encontrado la cajita. Estaba junto a. a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/01eeb50f4d311b1f93e394562b689b909cbd0ec14cc3f3b49fc5b482403063b4.mp3" }, { "id": "heldout-fr-4", "language": "fr", "sentences": [ "J’ai écrit le numéro sur l’enveloppe.", "Lis-le bien... et vérifie les deux derniers chiffres.", "Appelle-moi quand tu auras un moment." ], "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-4", "key": "01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Intense Interest. 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": "69581ff8b5d5ebf16e347f26195a82a9662b0782437d213267e99a65ddbdd9ec", "generation_seconds_batch": 17.918646815931424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9883348941802979, "target_z": 0.5976562772540401, "ce": 6.117925643920898, "genuineness": 4.381826400756836, "identity": 0.8343809843063354, "hypothesis": "J'écris le numéro sur l'enveloppe, lis le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "02a98392a270daa224142e68f0c4919a8e51d3e9db7c748072d52400ab5734cb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d3e718390964180af9ac7e312342efda1002a37da10e2e1fa766d37eb1459dbe", "generation_seconds_batch": 22.029708410962485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.784395694732666, "target_z": 2.5624999796231474, "ce": 5.744620323181152, "genuineness": 4.20609712600708, "identity": 0.325313925743103, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/02a98392a270daa224142e68f0c4919a8e51d3e9db7c748072d52400ab5734cb.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": "02b67d03a514208c27a2fe8d914280f4935bea4d36b4da851900435edec19451", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6680af95b4c2d5bcf15cbb01db2c2b26b2a8aad73ec63b0ed101990853241530", "generation_seconds_batch": 16.256331390002742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8203072547912598, "target_z": 1.5078123548149263, "ce": 6.38797664642334, "genuineness": 4.406930446624756, "identity": 0.5213632583618164, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/02b67d03a514208c27a2fe8d914280f4935bea4d36b4da851900435edec19451.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "032a735398fb4842ac05726c6ff383a4a3311321810d1dcb849c4e4392baed85", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3243c41053c5f03f1ad50968280fd96eb074f770748539c6374c2b861432d03d", "generation_seconds_batch": 22.57390055700671, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.534651756286621, "target_z": 1.195312684919936, "ce": 5.9431867599487305, "genuineness": 4.143336772918701, "identity": 0.6588274836540222, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/032a735398fb4842ac05726c6ff383a4a3311321810d1dcb849c4e4392baed85.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "0339e2ca3d5130673a895a2635d03658e61a3f72e8444ec2533ae178735f3ade", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2f5f26d677c49bb8616dd8ccf7fbcf23183cb81c57dc39d2720306116ceecbb6", "generation_seconds_batch": 15.332521051052026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.09409761428833, "genuineness": 3.8169827461242676, "identity": 0.42607009410858154, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0339e2ca3d5130673a895a2635d03658e61a3f72e8444ec2533ae178735f3ade.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": "034a1389431b0e2d862fec5851da428bcb43614238ba6b520bb39d6534b72c18", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd45c4768cb6e8f37d82320e49b5fb750cda14c1d4f4b663a1d787ab035b1020", "generation_seconds_batch": 17.334229354048148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.541792869567871, "target_z": 1.2031248767200426, "ce": 6.1020402908325195, "genuineness": 4.231201171875, "identity": 0.6678590178489685, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/034a1389431b0e2d862fec5851da428bcb43614238ba6b520bb39d6534b72c18.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": "03d3b32ca9771389fce5c9f8e9a6af61b933132f0e3fe177429cf389a6f0416d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "371865efcdd84242564e109eaeca65ddf4026bc8b3a8abf73e87d8dffbcb624d", "generation_seconds_batch": 20.68235179304611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.834590196609497, "target_z": 1.5234375208862738, "ce": 6.1020402908325195, "genuineness": 4.557555198669434, "identity": 0.6313169598579407, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/03d3b32ca9771389fce5c9f8e9a6af61b933132f0e3fe177429cf389a6f0416d.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "03ec2e3717bf504cc1a918e54c6ca37b102a291da8bca7ee1977864ea3c7d84c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7245165a75a8e5e5eff38b45f58df487e1b5323f084f8d973a70b0542f3b81d2", "generation_seconds_batch": 15.042259083944373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9274282455444336, "target_z": 1.6249999266433313, "ce": 6.0146708488464355, "genuineness": 4.218649387359619, "identity": 0.5041329264640808, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/03ec2e3717bf504cc1a918e54c6ca37b102a291da8bca7ee1977864ea3c7d84c.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "041aabd47a593be4e0cbbd49d0e1aff61a0a73d2aa2c4a3852b7831864b769ea", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dc9bba0323a0fc5bd4cf7981c1c1544cdccc50a5916fc7f7d294556e86e5eaa7", "generation_seconds_batch": 20.44154907995835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3132684230804443, "target_z": 0.9531250886393081, "ce": 6.308549880981445, "genuineness": 3.9048471450805664, "identity": 0.3413459360599518, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/041aabd47a593be4e0cbbd49d0e1aff61a0a73d2aa2c4a3852b7831864b769ea.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": "04395f6b39046445f26ec60130fc9bb9a510b5b8ad1988426dc0a8a4ebf27e18", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9267685d14fcd6996dfd0bc84a26d8d30c337bc4ae4e8368d62b1500c013021", "generation_seconds_batch": 15.402712606010027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.791946530342102, "target_z": 0.3828125259804869, "ce": 6.24500846862793, "genuineness": 4.457139015197754, "identity": 0.8051117062568665, "hypothesis": "La roue tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Ah je t'attendrai de l'autre côté.", "wer": 0.1, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/04395f6b39046445f26ec60130fc9bb9a510b5b8ad1988426dc0a8a4ebf27e18.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "044dac302d8c215f1dc77e5735578a09736ed469c3c5ad2600d1cf2a636aaa9e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "04b4fb8dc7c95561babf2cd34071ed167934b959e3ceb57ee3627b4ff4a5215e", "generation_seconds_batch": 22.460074800997972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8060245513916016, "target_z": 1.4921874495672902, "ce": 6.046441555023193, "genuineness": 4.293961524963379, "identity": 0.6790099740028381, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/044dac302d8c215f1dc77e5735578a09736ed469c3c5ad2600d1cf2a636aaa9e.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "0485f2d596e6c82b46c8d8881743d2dd9cb169e1047b98c6c973ead541cba838", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "711f799589a3943c3c33a4f45559aa8af5900400aeec352a3dab337f855e2851", "generation_seconds_batch": 20.475317662931047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.97405207157135, "target_z": 0.5820312415945483, "ce": 6.078212261199951, "genuineness": 4.645420074462891, "identity": 0.706216037273407, "hypothesis": "La porte est encore ouverte ? J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0485f2d596e6c82b46c8d8881743d2dd9cb169e1047b98c6c973ead541cba838.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": "04a066f2d69d59749fcf3c49d5277a51ce940d576c2e4b4a772dbe8934d53380", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Your message arrived after I had left.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7576b1dd09217b52b6b766cbff6942289d5624a6c406424791e5675f747faf6", "generation_seconds_batch": 20.338151767035015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7883758544921875, "target_z": 0.3789062996685778, "ce": 6.300607204437256, "genuineness": 4.030367851257324, "identity": 0.5257168412208557, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/04a066f2d69d59749fcf3c49d5277a51ce940d576c2e4b4a772dbe8934d53380.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "04aa96906ac00ce4ba3741e52fde3e9988affc64c41f6f6e01cc2862937924d0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "db57a60221ba77939c392ac00d77f220af3645302b89dc9582b06c0a4e276e7e", "generation_seconds_batch": 21.217900724965148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.255932331085205, "target_z": 1.9843748339286527, "ce": 5.959072113037109, "genuineness": 4.281409740447998, "identity": 0.5547464489936829, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder semble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/04aa96906ac00ce4ba3741e52fde3e9988affc64c41f6f6e01cc2862937924d0.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "04bcb0bdc0c84d639d4e60b47d91bc0fadce394f46786c1e077239367632df36", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7bbc64a45c89599b54d3ee0d40927b2e6bd3c7a1bd537d69b3a3094f95872927", "generation_seconds_batch": 19.99320493999403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.077397584915161, "target_z": 1.7890624750383557, "ce": 6.062326908111572, "genuineness": 3.986435890197754, "identity": 0.41497403383255005, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/04bcb0bdc0c84d639d4e60b47d91bc0fadce394f46786c1e077239367632df36.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "04db3ff8058caa5c76409d4db0f4aad9f2c85a518c9f9fad9eaa147264483cab", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c28cbe141229ae1500cc4219aa28bd3d04e0446d330e6034fe7a1b2761051d8a", "generation_seconds_batch": 19.34681889496278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.47752046585083, "target_z": 1.1328125422819688, "ce": 6.141753673553467, "genuineness": 4.231201171875, "identity": 0.343284010887146, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/04db3ff8058caa5c76409d4db0f4aad9f2c85a518c9f9fad9eaa147264483cab.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "058baa6211ad2f5fc2948f4d4e99b143cc5e6b6b78331f1ab1778858ec667f0b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3178bca1e4f628cd499631382eaed09992f8b21eddbaf519af474cdf80f77371", "generation_seconds_batch": 23.15144914900884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9202868938446045, "target_z": 1.6171874740195131, "ce": 5.863759994506836, "genuineness": 4.093128204345703, "identity": 0.6203426122665405, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/058baa6211ad2f5fc2948f4d4e99b143cc5e6b6b78331f1ab1778858ec667f0b.mp3" }, { "id": "heldout-de-0", "language": "de", "sentences": [ "Deine Nachricht kam, als ich schon weg war.", "Ich las sie zweimal... dann legte ich das Handy weg.", "Sag mir, wann wir reden können." ], "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-0", "key": "059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Intense Interest. 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": "416ae72e46ab4b420fb2d8afc0073d5acce13aec20104449d06963ceb572a846", "generation_seconds_batch": 15.946011116029695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2561371326446533, "target_z": 0.890624946001341, "ce": 6.38003396987915, "genuineness": 4.607763767242432, "identity": 0.6819427609443665, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "05fced9a85b376dfa3efd9487d2d07f3958cc54b48f3c65331d56914c7eba6d9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "13446865ae624ba6f4ac1876de2286ebd1ff8c4cd74be659c9ebe904751a855e", "generation_seconds_batch": 22.02536857605446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4416089057922363, "target_z": 2.18750016709019, "ce": 5.990842819213867, "genuineness": 4.105680465698242, "identity": 0.45866891741752625, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/05fced9a85b376dfa3efd9487d2d07f3958cc54b48f3c65331d56914c7eba6d9.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": "0674a92dd76f5166c8527092994eb5b9294aafca1745aeb7113ef00dc65216f1", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1704aabe2bfcff19db1f80a760b232474c50a643ec4e286a6bfc919d8db24c7", "generation_seconds_batch": 14.79766180505976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.35591197013855, "target_z": 2.0937499531332393, "ce": 6.292664527893066, "genuineness": 4.406930446624756, "identity": 0.4984610378742218, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0674a92dd76f5166c8527092994eb5b9294aafca1745aeb7113ef00dc65216f1.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "07442f2a7d5e203991748246cae3a630c870a3aee0993771d6c8ee6916470d08", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "92e7af6099bedc4a24b41af5c2286112a229a2800a8b3e420a7c373a3393d48e", "generation_seconds_batch": 23.195569848059677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.777459144592285, "target_z": 1.460937639072018, "ce": 5.967014789581299, "genuineness": 4.118232727050781, "identity": 0.5379111766815186, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/07442f2a7d5e203991748246cae3a630c870a3aee0993771d6c8ee6916470d08.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "08717c4567ca61969bc38145cc3ac9f1dd3c40ad28c50bffe24fa5ac5630c019", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "86a2fbe15b66f149dd8d477e6b4740ef7e3b675ced971a5d10a2085752d93c6c", "generation_seconds_batch": 18.354161667986773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.013124942779541, "target_z": 1.7187498797765706, "ce": 5.9431867599487305, "genuineness": 4.319066047668457, "identity": 0.6672488451004028, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.2631578947368421, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/08717c4567ca61969bc38145cc3ac9f1dd3c40ad28c50bffe24fa5ac5630c019.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "088018f50f4d078b1a413a3adc55c8badcfd7242802501f2c44e80d11e13e159", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "79ec7b527f6f1285d2bf48784031c22a37adc2a1a696be20c79303aa912651ee", "generation_seconds_batch": 22.679797998978756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.841731548309326, "target_z": 1.5312499735100917, "ce": 5.959072113037109, "genuineness": 4.080576419830322, "identity": 0.6554760932922363, "hypothesis": "La porte est encore ouverte! J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/088018f50f4d078b1a413a3adc55c8badcfd7242802501f2c44e80d11e13e159.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": "08e7449fffa5a0b9aeffc0f76cf32bc9d639636bb93d1fe6da3d800e1a301040", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "96c719e1337c1e9f1c6936c84ff4ae0a36a1e3c3b7f1c0e27f94e595ab10a4f7", "generation_seconds_batch": 20.66980470204726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9202868938446045, "target_z": 1.6171874740195131, "ce": 6.348263263702393, "genuineness": 4.281409740447998, "identity": 0.7376397848129272, "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/emo_Interest/08e7449fffa5a0b9aeffc0f76cf32bc9d639636bb93d1fe6da3d800e1a301040.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "08f1e658e43648cdffd328e7a54db62b09dcb136318a933b29bbf7c33a3e4afd", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b25704b3ef03dc3526e2f90a2e0a903adf67636673e108c206334755fa41597a", "generation_seconds_batch": 19.83091966493521, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2597079277038574, "target_z": 0.8945313027251057, "ce": 5.804190158843994, "genuineness": 3.9173994064331055, "identity": 0.4804597496986389, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/08f1e658e43648cdffd328e7a54db62b09dcb136318a933b29bbf7c33a3e4afd.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": "08fd6e9257d110c6161eda6f0fd2e698c045acc12280bbc537e0d7b8db2d98c2", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "79c39187769eea80f47736c72e426a50d503906f28a0543486fa1616e2744194", "generation_seconds_batch": 20.645170028088614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.852648377418518, "target_z": 0.44921876451850734, "ce": 6.1020402908325195, "genuineness": 4.494794845581055, "identity": 0.7363380193710327, "hypothesis": "La route tourne à gauche, après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/08fd6e9257d110c6161eda6f0fd2e698c045acc12280bbc537e0d7b8db2d98c2.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "0923e4885c18c16bfb70575673da9ffcde0d2e0bcc66a0a16023598120afeed0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3d817390debb79f38fe07627b026e74794a427418625f0d4b237c358d5e2e0cd", "generation_seconds_batch": 19.936314187943935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2811319828033447, "target_z": 0.9179686605965599, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.3761550784111023, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0923e4885c18c16bfb70575673da9ffcde0d2e0bcc66a0a16023598120afeed0.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "098d52f6f5fdf86dfa6aa5055138d25e9e01026cf2ef52781b22027cbab0b784", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "50b9257b3951b8c67e9434e497c433cf04868a2f8104c77b47986c4cc02c015b", "generation_seconds_batch": 19.777131546055898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9845595359802246, "target_z": 1.6875000692812983, "ce": 6.165581703186035, "genuineness": 4.319066047668457, "identity": 0.693901777267456, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/098d52f6f5fdf86dfa6aa5055138d25e9e01026cf2ef52781b22027cbab0b784.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "09bd2d17c52824e9d2c6fcf8e942cefbd6f0d3c117d92662db69b85b056d8c94", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8a9e7ef87c84a97a03dd7063efcd218ecb4622399ce493d2c84b822b89aed10a", "generation_seconds_batch": 15.000229672063142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6132068634033203, "target_z": 1.281249924605646, "ce": 6.157639026641846, "genuineness": 4.055472373962402, "identity": 0.6528167724609375, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/09bd2d17c52824e9d2c6fcf8e942cefbd6f0d3c117d92662db69b85b056d8c94.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "09e95614c70a61ec91238fffcad4687f684e5d9b098ddd295e294ec00b95c855", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f2907539b6317ac2182a8fe60aa6d14be609b46baf0411c632dcc53e8ed2ee67", "generation_seconds_batch": 15.484136654995382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6044849157333374, "target_z": 0.177734405692634, "ce": 6.229123115539551, "genuineness": 4.720732688903809, "identity": 0.43723711371421814, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/09e95614c70a61ec91238fffcad4687f684e5d9b098ddd295e294ec00b95c855.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "0afd1c251dd5bc0ea521be4a5daee7f834d1d2cd46b76e93f68f215a59f62814", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "eb33ed34282eab72380144f9f7753ec3ad5e92aa329b13596ba2335eac0faf56", "generation_seconds_batch": 20.586263173958287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0916805267333984, "target_z": 1.8046876411097033, "ce": 6.300607204437256, "genuineness": 4.268857479095459, "identity": 0.651449978351593, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0afd1c251dd5bc0ea521be4a5daee7f834d1d2cd46b76e93f68f215a59f62814.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "0b337ab230cc0ace5a1beafd5e6f23d635b7d6b621f8d37fc64673a19b6a1e11", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "549f2ffa829f17e893a7637077fc736f70335624d189d5c460aa2c0f99894307", "generation_seconds_batch": 19.78528204304166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.356205940246582, "genuineness": 3.986435890197754, "identity": 0.4639488458633423, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0b337ab230cc0ace5a1beafd5e6f23d635b7d6b621f8d37fc64673a19b6a1e11.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "0b9fd57a5578cb024d65939817a97f95524b7a9f5c0f3441633cd4a6b26453b3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1e8d6a2afb7ef927ac31586f3d36d233ee2948f222520059d38d9d1126c812d6", "generation_seconds_batch": 22.080986079992726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6346311569213867, "target_z": 1.3046875433008114, "ce": 6.252951145172119, "genuineness": 4.482243061065674, "identity": 0.6817505955696106, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0b9fd57a5578cb024d65939817a97f95524b7a9f5c0f3441633cd4a6b26453b3.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "0ba0bd067ed551f50548a48abe4deb99b678adb145ad528a143f8d4c3e26babb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a15c7fedfa0d25b65ef0df0d3988f147aedf8daba2aa14930d512028095b9031", "generation_seconds_batch": 20.18212297698483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3846821784973145, "target_z": 1.0312498757012, "ce": 6.308549880981445, "genuineness": 4.457139015197754, "identity": 0.5111980438232422, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0ba0bd067ed551f50548a48abe4deb99b678adb145ad528a143f8d4c3e26babb.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "0bb8f21796a14d8069b26cbbbdab7c334a9324cbd7cf22443c208f1db52f7bf6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d65fb2d37df98f6d46066b0baecf0e99649c4e601b077f8bcf8b4562b204d987", "generation_seconds_batch": 21.882110688020475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.070460796356201, "target_z": 0.6874998736635148, "ce": 5.974957466125488, "genuineness": 4.381826400756836, "identity": 0.5303731560707092, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0bb8f21796a14d8069b26cbbbdab7c334a9324cbd7cf22443c208f1db52f7bf6.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": "0bd6f1cbd4766cef32024f1ac765a1a2bb748cfe7b727b32a4f4fe4931cff4ce", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ae250c5bbfeb97571089ceb7a0ec5155f6aa27afcad6c1ef8b15986decb9cce", "generation_seconds_batch": 20.745220619020984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.298780918121338, "target_z": 2.0312500713189836, "ce": 6.316492557525635, "genuineness": 4.394378662109375, "identity": 0.5881264209747314, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0bd6f1cbd4766cef32024f1ac765a1a2bb748cfe7b727b32a4f4fe4931cff4ce.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "0befe9bfcbcaff4ff16a5c53e64b54708bd618481abc8e6b64b88d28352f62d0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e32afb2467adb2a439b3ce54c3cc67f0e1901611fe5c6714692ea67ba978a5a8", "generation_seconds_batch": 15.042887161951512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.777459144592285, "target_z": 1.460937639072018, "ce": 6.2767791748046875, "genuineness": 4.444586753845215, "identity": 0.6519757509231567, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0befe9bfcbcaff4ff16a5c53e64b54708bd618481abc8e6b64b88d28352f62d0.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "0bf1e58a7ba26fe036dac37c99386525be3a79efd45e61937defafc662c3dc5c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "637f980d21df11c0cccf45cd97d620876b89cd58c46400ece67e527c31b4be19", "generation_seconds_batch": 22.431671927915886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8631558418273926, "target_z": 1.5546875922052572, "ce": 5.780362129211426, "genuineness": 3.7416701316833496, "identity": 0.35264408588409424, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0bf1e58a7ba26fe036dac37c99386525be3a79efd45e61937defafc662c3dc5c.mp3" }, { "id": "heldout-nl-4", "language": "nl", "sentences": [ "Ik schreef het nummer op de envelop.", "Lees het goed... en controleer de laatste twee cijfers.", "Bel me wanneer je even tijd hebt." ], "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-4", "key": "0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Intense Interest. 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": "64037ea3ec8915bf3e01459ed691edd6c2045e4b14e91276d63b72dfc08b3e23", "generation_seconds_batch": 17.793920486001298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.470378875732422, "target_z": 1.1249998288344394, "ce": 6.181467056274414, "genuineness": 4.331617832183838, "identity": 0.7510819435119629, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "0cdf1fec9f73249d66f45014112ccaafb95cfff04231bf270b16b85c5e7e0e6a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6cfa8d0ab4e3909b1733f99475776175185795f7418a81601f9a62cf92b4302a", "generation_seconds_batch": 20.843670643982477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.184518575668335, "target_z": 1.9062500468667607, "ce": 5.720792293548584, "genuineness": 3.998987913131714, "identity": -0.04001304507255554, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0cdf1fec9f73249d66f45014112ccaafb95cfff04231bf270b16b85c5e7e0e6a.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": "0ce33bc256550ac962b3eb5c93f85457758c962bb5d3aa9e8d42333647a64a0a", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30c6108962b50f3be5fc864c5681a56f32a231f0d023da870462ea1669e9ee0a", "generation_seconds_batch": 15.3320644950727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0916805267333984, "target_z": 1.8046876411097033, "ce": 6.403861999511719, "genuineness": 4.457139015197754, "identity": 0.5946567058563232, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0ce33bc256550ac962b3eb5c93f85457758c962bb5d3aa9e8d42333647a64a0a.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "0d2b8f80e01e490034da36dbc214f3e4ffedbf52150b7220a7a53ca1230ea65d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a1f80f7a325126208f9395b81c38baf001cc0c0127eefd7008731289a9efbf6d", "generation_seconds_batch": 21.801082237041555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.663196563720703, "target_z": 1.3359373537960837, "ce": 6.149696350097656, "genuineness": 3.7918784618377686, "identity": 0.407033234834671, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0d2b8f80e01e490034da36dbc214f3e4ffedbf52150b7220a7a53ca1230ea65d.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "0ec980a9a3f3953e55dce8b6914d2849b8959e3a6aef9aae8e5219c39310b244", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2ce745659c34fc417dda6726efd5173b893553feb202a84051fb77a1198c95fa", "generation_seconds_batch": 15.226053628022783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4989447593688965, "target_z": 1.1562501609771343, "ce": 6.09409761428833, "genuineness": 4.105680465698242, "identity": 0.20672400295734406, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0ec980a9a3f3953e55dce8b6914d2849b8959e3a6aef9aae8e5219c39310b244.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "0ed8172c283f87313d518a7f7cfc35b931e4e99d36c0c736f7b84a87df5f60d1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5930b72d6c2800bf9a19bc62e36aceb7d44e5743987ff7a4a37d713d28261ef2", "generation_seconds_batch": 19.893245415994897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.527510166168213, "target_z": 1.1874999714724066, "ce": 6.300607204437256, "genuineness": 4.168440818786621, "identity": 0.3059614300727844, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0ed8172c283f87313d518a7f7cfc35b931e4e99d36c0c736f7b84a87df5f60d1.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "0f332a2a4efc8dd49752996f949b650fd1f874236a73cac4f6448387adcf7594", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1f7233e72dbf8976c3b2d41686c2fba6cf0b290987a62e630eee165747730ba6", "generation_seconds_batch": 15.376002733013593, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.248791217803955, "target_z": 1.9765626421285458, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.6255122423171997, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0f332a2a4efc8dd49752996f949b650fd1f874236a73cac4f6448387adcf7594.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "0f3e444c1ae56821286076506d4177fcc1df125564bdab06ff2a7a3d9d7442ff", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "321c071100562abb5c6c319d868e83af0201b56a83edd63ec57021e9a826391a", "generation_seconds_batch": 21.64453279110603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.291844129562378, "target_z": 0.9296874699441426, "ce": 6.022613525390625, "genuineness": 3.9550557136535645, "identity": 0.26641637086868286, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0f3e444c1ae56821286076506d4177fcc1df125564bdab06ff2a7a3d9d7442ff.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "0f6578b39542878e431ccb78b0380afd00a7f21c20ecff5c0d78bc4da6fb0d74", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "73dca89e50bc38b539d56125bbe3bbc50663fbc8931585629e1f4593ce3a9dfb", "generation_seconds_batch": 20.791929512983188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.197352409362793, "genuineness": 4.532451152801514, "identity": 0.7361836433410645, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0f6578b39542878e431ccb78b0380afd00a7f21c20ecff5c0d78bc4da6fb0d74.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "0f8bf6d86b4262441795fee0fbe1e3a16694d6c1d61358b2e805f78601e3d41e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "01df618a4a3d608930272a57b8c2051d365b3d4b5a0da8810d9743c41eb83684", "generation_seconds_batch": 19.97549504903145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1525869369506836, "target_z": 0.7773437308967008, "ce": 6.435632705688477, "genuineness": 4.331617832183838, "identity": 0.5272278189659119, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0f8bf6d86b4262441795fee0fbe1e3a16694d6c1d61358b2e805f78601e3d41e.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "0f9b320bcf390a77869a3ea1487a703f69b72a47a9e65bf615db17d5ba1cee97", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0e9541f8c2d7108917e298a016f77f24492bd8569de788cc1f470c0c05e0301f", "generation_seconds_batch": 22.022942226030864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3846821784973145, "target_z": 1.0312498757012, "ce": 6.125868320465088, "genuineness": 4.381826400756836, "identity": 0.749927818775177, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0f9b320bcf390a77869a3ea1487a703f69b72a47a9e65bf615db17d5ba1cee97.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "0fbd29de5f5b82c7ebe35f2070aa75454196538c1af6f98d3ccd8e909e95e145", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "193cc17fd9dff41ead499b457815c64b9d780a7f17af9474cc9841967bc4e8ab", "generation_seconds_batch": 23.83501401299145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0416905879974365, "target_z": 1.7499999510955542, "ce": 6.022613525390625, "genuineness": 3.9048471450805664, "identity": 0.055889301002025604, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0fbd29de5f5b82c7ebe35f2070aa75454196538c1af6f98d3ccd8e909e95e145.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": "0fbff33b625b7547a8ac81c2ee0a0f90c11bc12b6c6c13e1f1e133b713dd5380", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The keys are on the kitchen table.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "873bae60855e4040711b362eb8185b7a99c540e75f77af1962abeefd298dc9a1", "generation_seconds_batch": 15.348801995045505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.998842239379883, "target_z": 1.7031249745289345, "ce": 6.316492557525635, "genuineness": 4.105680465698242, "identity": 0.5550436973571777, "hypothesis": "The keys are on the kitchen table. I checked the drawer. Then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/0fbff33b625b7547a8ac81c2ee0a0f90c11bc12b6c6c13e1f1e133b713dd5380.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "105984689e7e824299fea574f2c6a50c66821ba59fd3c8f9ef11cf75ba07152c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dc91a118e1f2a90509dd6359c69f73c6630d77fa5de1c16083379353d0ee7e7d", "generation_seconds_batch": 23.56388650496956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.955993890762329, "target_z": 1.6562499979623146, "ce": 6.197352409362793, "genuineness": 4.1998209953308105, "identity": 0.2990700900554657, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/105984689e7e824299fea574f2c6a50c66821ba59fd3c8f9ef11cf75ba07152c.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "107ef650138405c2cd4060225d20e7bba7fe50563647ed527df495b88af4b143", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7d84c365c29bbf3d3d205ea17f761cee30e8c94868fee5858300daacd3dfd783", "generation_seconds_batch": 19.37749345100019, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7417521476745605, "target_z": 1.4218751151292164, "ce": 5.911416053771973, "genuineness": 3.9173994064331055, "identity": 0.11885475367307663, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/107ef650138405c2cd4060225d20e7bba7fe50563647ed527df495b88af4b143.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": "10b6d670d463156bc71b02bbf085ed71e189d10552bc75468ae3bdace7c02e27", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b38f2cf30bba35d10bb6138d0117bb27eb666d30b3d71a91de4a8ad5e9ba60d6", "generation_seconds_batch": 20.626700583961792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3275511264801025, "target_z": 0.9687499938869443, "ce": 6.149696350097656, "genuineness": 4.293961524963379, "identity": 0.6491842865943909, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/10b6d670d463156bc71b02bbf085ed71e189d10552bc75468ae3bdace7c02e27.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "11525b8cc6580c5ce2d0ea05724b357127332fa6275fe027937aca2529638018", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "34b82d12b1a76654e7868c13ca3543717729358903d289d28b2b42025b2ad9b1", "generation_seconds_batch": 20.540664230939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0240418910980225, "target_z": 0.6367188011968418, "ce": 6.09409761428833, "genuineness": 4.356721878051758, "identity": 0.4905281662940979, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/11525b8cc6580c5ce2d0ea05724b357127332fa6275fe027937aca2529638018.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": "1163e4ed30c8071491b1eaee36e72bc4a0fc67c257b3970d069907957366a333", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Escribí el número en el sobre.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d19014c95605d962aa1f0f05f1acea2eb4b7bd2a7d1182de1d5bb9a01ccdc7a", "generation_seconds_batch": 14.862233455991372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5060858726501465, "target_z": 1.1640623527772411, "ce": 6.062326908111572, "genuineness": 4.218649387359619, "identity": 0.46733391284942627, "hypothesis": "Escribí el número en el sobre, léelo bien, y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1163e4ed30c8071491b1eaee36e72bc4a0fc67c257b3970d069907957366a333.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "1180ff318f7ce7a220af4ca371dbd457b62156f97e41e10df3ef7196516a03e7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6ed6f35903480d0407a00fdc8e306811c1f08b327fb384bb5fbec3c845ba0abe", "generation_seconds_batch": 19.755011534085497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.541792869567871, "target_z": 1.2031248767200426, "ce": 6.213237762451172, "genuineness": 4.250029563903809, "identity": 0.3887818455696106, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1180ff318f7ce7a220af4ca371dbd457b62156f97e41e10df3ef7196516a03e7.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "1230038d72448990526015bcd9af52b4d4c9ba796d5e2519747f1b5b5c53148f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bd96ff62263ac7e9f688d1a2a94e3aff03eed650b59cbf43cb92d044b7d22e7f", "generation_seconds_batch": 20.454305037041195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.520368814468384, "target_z": 1.1796875188485885, "ce": 6.181467056274414, "genuineness": 4.281409740447998, "identity": 0.6439511775970459, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1230038d72448990526015bcd9af52b4d4c9ba796d5e2519747f1b5b5c53148f.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": "12a46f72f8ce83d781500e09d7dfd50bc533d211aab9df0e3a5bcba229859b3b", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The keys are on the kitchen table.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d5b1a27896d8be91a38cc1fd36060989b0b4de6a34b8076c135c000f7b5852b9", "generation_seconds_batch": 21.553609560942277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.777459144592285, "target_z": 1.460937639072018, "ce": 6.38797664642334, "genuineness": 4.281409740447998, "identity": 0.5000451803207397, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/12a46f72f8ce83d781500e09d7dfd50bc533d211aab9df0e3a5bcba229859b3b.mp3" }, { "id": "heldout-es-0", "language": "es", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-0", "key": "12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Intense Interest. 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": "c9fc8c8ee5f8d569d0db267672c8855017f9f5a6cde9f209b98703ae141ec419", "generation_seconds_batch": 15.413211503066123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.345404624938965, "target_z": 0.988281255858345, "ce": 6.252951145172119, "genuineness": 4.105680465698242, "identity": 0.5618007183074951, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "132ee27fa19dc0c6acee88f5cf98a73db66cf447387ad36bfaeacae10f8e1d32", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "64af80eac623e70d8335bdae96866534eb2a5e7f6abd4dfea02d115f00d80817", "generation_seconds_batch": 20.84375582600478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2561371326446533, "target_z": 0.890624946001341, "ce": 6.427689552307129, "genuineness": 4.3127899169921875, "identity": 0.5677445530891418, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/132ee27fa19dc0c6acee88f5cf98a73db66cf447387ad36bfaeacae10f8e1d32.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "1343403ef7e5199ee8c53d64d1bf9624bbc03eb0e29e9bbfb38c16b3698995d0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f7d880584f1fffb1165e693ce2870b9645c6cbc319efc26711880d1b0fd5a0a2", "generation_seconds_batch": 21.031932740006596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.298780918121338, "target_z": 2.0312500713189836, "ce": 6.316492557525635, "genuineness": 4.557555198669434, "identity": 0.5805246829986572, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1343403ef7e5199ee8c53d64d1bf9624bbc03eb0e29e9bbfb38c16b3698995d0.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": "13707e469f3ef5c973b91ff0bc2ec62838c8e8f1562307a0632511a2c45375e0", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65d39ff1d05754e9d97c105b2b71d38d0b821e79491b45e3d1f90522b1ce78ed", "generation_seconds_batch": 15.497880470007658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8131661415100098, "target_z": 1.5000001630148196, "ce": 6.260893821716309, "genuineness": 4.482243061065674, "identity": 0.6760650277137756, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/13707e469f3ef5c973b91ff0bc2ec62838c8e8f1562307a0632511a2c45375e0.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "139b65004894a1003d03a10d0a82ff0b77df123849dae6c3c5438599c6789feb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "353f4815ab03273be18fd34a10e2c356a3cd3c4f305efcb1295cd98d092636a8", "generation_seconds_batch": 15.372660969034769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.941710948944092, "target_z": 1.6406248318909673, "ce": 5.685050010681152, "genuineness": 4.030367851257324, "identity": 0.3619253933429718, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/139b65004894a1003d03a10d0a82ff0b77df123849dae6c3c5438599c6789feb.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "13b05cbddba8d8d9257267dc6d322e6349f4c53b63525671666b6bf1b3fccec2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "68c186798ca63cc44ed7ad2acaa9309587337a651b694b57c1d9a1a79796a49c", "generation_seconds_batch": 15.30385332996957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.34897518157959, "target_z": 0.9921873517583985, "ce": 6.133810997009277, "genuineness": 4.532451152801514, "identity": 0.5616096258163452, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/13b05cbddba8d8d9257267dc6d322e6349f4c53b63525671666b6bf1b3fccec2.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "144512f7247fdc04154659a75a1d8667c146336b56edea3471a5e8a5353e19e2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6e7c4ed738b3e0090b252be68479e4a0f442e50891c7b2ebc71215375871c94d", "generation_seconds_batch": 22.0735661649378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.102597236633301, "target_z": 0.722656301706263, "ce": 5.903473377227783, "genuineness": 4.432034492492676, "identity": 0.4326741695404053, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/144512f7247fdc04154659a75a1d8667c146336b56edea3471a5e8a5353e19e2.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": "14834e2ab329021966dea06e976e5b2f78fb75e5366a2b74173d995b857559e1", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78174e02a922271ba03a89f171fe1c9a93f613fca62497afb787af49bc8bdd0b", "generation_seconds_batch": 14.860916550969705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0274078845977783, "target_z": 1.734375045847918, "ce": 6.125868320465088, "genuineness": 4.306513786315918, "identity": 0.6260730028152466, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. ¡Llévatelas cuando te vayas!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/14834e2ab329021966dea06e976e5b2f78fb75e5366a2b74173d995b857559e1.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "1487670ea743dc8317441896546052ef94bdf2aea91a9e0aad1861025180ea61", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "414658c1ee4dc111400758e8f4ef3d30a5dbeda4d2382ed1fcae3b27ac1bdb8e", "generation_seconds_batch": 16.83194933796767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1990060806274414, "target_z": 0.8281250641870852, "ce": 6.252951145172119, "genuineness": 4.394378662109375, "identity": 0.532296359539032, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1487670ea743dc8317441896546052ef94bdf2aea91a9e0aad1861025180ea61.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Intense Interest. 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": "2dd73cbe2e8ed3c504ee6cf207bd882df81f4d9a974e70f49a60ad738d96034f", "generation_seconds_batch": 15.63570584799163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.881213903427124, "target_z": 0.4804687054256353, "ce": 6.300607204437256, "genuineness": 4.400654315948486, "identity": 0.4803009331226349, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zum kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "1593ac3b5b45805f9fb8c6478f666422956ea47581b42a30b911bcf53b8ac606", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e39b1b3fde0d219c8588af22245807e71a5c1bbbc5d1520bd0887ed3aba9befc", "generation_seconds_batch": 21.053300500032492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.055973529815674, "target_z": 1.7656251171669015, "ce": 6.23706579208374, "genuineness": 4.400654315948486, "identity": 0.644256591796875, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1593ac3b5b45805f9fb8c6478f666422956ea47581b42a30b911bcf53b8ac606.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "16b200f8d31bccbf91f96ffacdf6427e7544fa68f75055e9ac3806a7040f928d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ee36d9c7f955c550efea99d25047bd42789f0c908373df73d75b9456de2568e1", "generation_seconds_batch": 15.219877628958784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6774795055389404, "target_z": 1.351562519867431, "ce": 6.149696350097656, "genuineness": 4.149612903594971, "identity": 0.054040487855672836, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/16b200f8d31bccbf91f96ffacdf6427e7544fa68f75055e9ac3806a7040f928d.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "16f3bf6147eabf3e757bbd7cb2a64c29d237d325e821ab3fd170773ecbdb7e64", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa064fc18744b2a39a2f6e2c35285f84c6b6a42878f4f3dec63d896278cd690e", "generation_seconds_batch": 23.01652722398285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9883348941802979, "target_z": 0.5976562772540401, "ce": 5.990842819213867, "genuineness": 4.281409740447998, "identity": 0.6007599830627441, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/16f3bf6147eabf3e757bbd7cb2a64c29d237d325e821ab3fd170773ecbdb7e64.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "1724d727b47049eff691bf7cb8b8ab5ba8b277e82281339dfc09a4f6f46e8c46", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "941567933800b1bb27b0918805918be63b6d54333944d49958c23d9d1191b1c2", "generation_seconds_batch": 19.84660206909757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.527510166168213, "target_z": 1.1874999714724066, "ce": 6.284721851348877, "genuineness": 3.9550557136535645, "identity": 0.3727691173553467, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1724d727b47049eff691bf7cb8b8ab5ba8b277e82281339dfc09a4f6f46e8c46.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": "17b36f1fe1f043475f471eab396b4f0cfdbdcfbe63089136f773f4d69adf82f5", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "38653698ff790fdcfcc5c11df8b52f19ae2f6984e2e377a4d962a86bac6d3706", "generation_seconds_batch": 20.57794175692834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.706045150756836, "target_z": 1.3828125911864146, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.7693387866020203, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/17b36f1fe1f043475f471eab396b4f0cfdbdcfbe63089136f773f4d69adf82f5.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "17f144623ad6bbed46c46178c6168599b3d18a7943e04b4a897be6fb1e21ca3b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "39b2a3759e2958bd4008a8f37ced492ca01a6603ecc01115ab67c786bbd3e017", "generation_seconds_batch": 20.48681285197381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5703585147857666, "target_z": 1.2343749480390263, "ce": 6.117925643920898, "genuineness": 4.042920112609863, "identity": 0.5746985673904419, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/17f144623ad6bbed46c46178c6168599b3d18a7943e04b4a897be6fb1e21ca3b.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "1858fbd16b60e9c8b549e394dc85871f4ffe8984e4ba0e01968ca0779e599989", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b163e6bce69379aeca9b59090ba426070ff09a5baea1c0c326dfd4424ad16475", "generation_seconds_batch": 21.076050044968724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8560142517089844, "target_z": 1.546874878757728, "ce": 6.213237762451172, "genuineness": 3.9299514293670654, "identity": 0.4805486798286438, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1858fbd16b60e9c8b549e394dc85871f4ffe8984e4ba0e01968ca0779e599989.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "1990e803190329316341de0938a3994507f616f1e9b6b1aeed77793835f9a3b8", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0ed9cb22fa0d9325455b6602146e89352eca2a7f6081ba61a4d555f8d20579ce", "generation_seconds_batch": 15.348714818013832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.106167793273926, "target_z": 0.7265623976063165, "ce": 6.372091293334961, "genuineness": 4.444586753845215, "identity": 0.7127418518066406, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1990e803190329316341de0938a3994507f616f1e9b6b1aeed77793835f9a3b8.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "1a06ea01b4ba7f4f073e1afb5b11c37d7be6da61c9517e04590050797c1a6238", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "39bb0008d4e0b8d1f03d11e47a912cf486a46e5ee61160faae5d2406b595a398", "generation_seconds_batch": 20.704770711949095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3703994750976562, "target_z": 1.015624970453564, "ce": 6.23706579208374, "genuineness": 4.425758361816406, "identity": 0.4302581548690796, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1a06ea01b4ba7f4f073e1afb5b11c37d7be6da61c9517e04590050797c1a6238.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "1a4be54066780aa6f19a156435b170168a5cd182afe1ffc23aa413e3fe09fff7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "746a260b62feaca2e76713f21c0510905a96cb425db68ad17fa67b4fb9e58d08", "generation_seconds_batch": 17.574152011075057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.3641486167907715, "genuineness": 4.268857479095459, "identity": 0.48158228397369385, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1a4be54066780aa6f19a156435b170168a5cd182afe1ffc23aa413e3fe09fff7.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "1ab586729aab648562305ddfb197bbfdf12a67ea4a8ded9f917399b57fc21141", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7c6bb94ea9032faa6d1718f1466d96a7784e67791b66f293eb165b8865db0206", "generation_seconds_batch": 22.551954924943857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.720327854156494, "target_z": 1.398437496434051, "ce": 6.078212261199951, "genuineness": 3.873466968536377, "identity": 0.4785456657409668, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1ab586729aab648562305ddfb197bbfdf12a67ea4a8ded9f917399b57fc21141.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "1b07efa11447d34f73976ab09993f44a96445250f0e4203652abca24b9b96486", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7b2b1b186964393bd0a40a372c52d9104d71efd18c9f7500ef83c4040e40776f", "generation_seconds_batch": 20.137151267030276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8847846984863281, "target_z": 0.48437506214939996, "ce": 6.348263263702393, "genuineness": 4.482243061065674, "identity": 0.5970451831817627, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1b07efa11447d34f73976ab09993f44a96445250f0e4203652abca24b9b96486.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "1b41bfe4d3018d15321174361a390149b5412267e979bf0ab7b4d920b9a2114b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "48d1a3252ddf3e830810371f8d090ebf974dbfef9e4f03e4511cdfdc891267e5", "generation_seconds_batch": 16.62863296701107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.427325963973999, "target_z": 2.171875001018843, "ce": 6.070269584655762, "genuineness": 4.250029563903809, "identity": 0.5996080040931702, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1b41bfe4d3018d15321174361a390149b5412267e979bf0ab7b4d920b9a2114b.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "1b545fc5811f749c4814a948887297dc5e39a71971a96337a598e1e14e22959f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5827a3d5963cea3e4a9e20de0c0d533dc2d4607c682c4079b23ca0e1bcbdb749", "generation_seconds_batch": 22.34117997100111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.598719596862793, "target_z": 2.3593751681090325, "ce": 6.157639026641846, "genuineness": 4.2751336097717285, "identity": 0.4558982849121094, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1b545fc5811f749c4814a948887297dc5e39a71971a96337a598e1e14e22959f.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "1c41ae461f8026b4beb1c5363a6a5b07f1451d05405c4b46de7882f0251277ad", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1889313006d255b1fae6f8119b25cc69429777d997a7be1733c7253ead0f306", "generation_seconds_batch": 20.329823613050394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 6.2767791748046875, "genuineness": 3.9801597595214844, "identity": 0.22631756961345673, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1c41ae461f8026b4beb1c5363a6a5b07f1451d05405c4b46de7882f0251277ad.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "1cc84b30a864eda621a8062a19926ec1eb6b98d4468104fbde324751a90898d9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4ed9727e45216a9eb454fe6e1e157e4e9d1c28da9d3f666416731d7f379aa304", "generation_seconds_batch": 14.769592819036916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.998842239379883, "target_z": 1.7031249745289345, "ce": 5.982900142669678, "genuineness": 4.18726921081543, "identity": 0.558667004108429, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1cc84b30a864eda621a8062a19926ec1eb6b98d4468104fbde324751a90898d9.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "1d4720cca5aaf6ca8bb7c089a0e6ccf2ecd92a06d89e175e25cea6f70af53e2b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4a066740bf3550aef8124c1471fc13d2059e2451d733293bf39e5d699e9ab372", "generation_seconds_batch": 20.324017529026605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4489548206329346, "target_z": 1.1015624709629852, "ce": 6.300607204437256, "genuineness": 4.406930446624756, "identity": 0.47247156500816345, "hypothesis": "Ah, la porte est encore ouverte ! J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Hein ?", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1d4720cca5aaf6ca8bb7c089a0e6ccf2ecd92a06d89e175e25cea6f70af53e2b.mp3" }, { "id": "heldout-es-4", "language": "es", "sentences": [ "Escribí el número en el sobre.", "Léelo bien... y comprueba las dos últimas cifras.", "Llámame cuando tengas un momento." ], "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-4", "key": "1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Intense Interest. 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": "9afa215d6674ab4ac4cdd1f3f10e4d3924f6bd810566a9d5afdbb19822194c2c", "generation_seconds_batch": 16.052075329003856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0883145332336426, "target_z": 0.7070313964586269, "ce": 6.24500846862793, "genuineness": 4.18099308013916, "identity": 0.5710501074790955, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "1d61a9ff892ca4f34d770ba69d3b02d9920d515096965ea288c603793f678ce7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c58782c38ff5aa2e03fc490b9f5e8cb70029a1fceb0f277196ad0c732fcaef83", "generation_seconds_batch": 19.896188564947806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.784600257873535, "target_z": 1.4687498308721247, "ce": 6.109982967376709, "genuineness": 3.9425034523010254, "identity": 0.15181389451026917, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1d61a9ff892ca4f34d770ba69d3b02d9920d515096965ea288c603793f678ce7.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Intense Interest. 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": "6d69d6c8c34dcb41b4503274762ac280be81a99db745fa42c2c5b168d7e11b70", "generation_seconds_batch": 15.53630890196655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0811729431152344, "target_z": 0.6992186830110976, "ce": 6.435632705688477, "genuineness": 4.300237655639648, "identity": 0.5432301163673401, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "1dbc7303b46dc60bee5c35a23df7da5172e0750628df75e1923d8f1049905919", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ab6fd71ca1294b33d600df6f4d9d3ae11f50f264da673ac44bfce05b995e8c2f", "generation_seconds_batch": 20.486618498922326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6132068634033203, "target_z": 1.281249924605646, "ce": 6.268836498260498, "genuineness": 4.168440818786621, "identity": 0.4297824501991272, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1dbc7303b46dc60bee5c35a23df7da5172e0750628df75e1923d8f1049905919.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "1e46ee33888751d5e26aa317c8fe7d501e4c5ee32e04c96e26e20be72fd90814", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "57ce63d1e483d15bb6f35f41cd9342d06e9318c688ee9648362db4dd9204a97a", "generation_seconds_batch": 23.21115234401077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1630945205688477, "target_z": 1.8828126889953065, "ce": 5.534139156341553, "genuineness": 3.7291181087493896, "identity": 0.0019311346113681793, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1e46ee33888751d5e26aa317c8fe7d501e4c5ee32e04c96e26e20be72fd90814.mp3" }, { "id": "heldout-es-4", "language": "es", "sentences": [ "Escribí el número en el sobre.", "Léelo bien... y comprueba las dos últimas cifras.", "Llámame cuando tengas un momento." ], "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-4", "key": "1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Intense Interest. 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": "f5151a528b98dd6ad45dc052085ea7462a27a77267b539f417bd11b03c024964", "generation_seconds_batch": 16.052075329003856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 6.229123115539551, "genuineness": 4.268857479095459, "identity": 0.6808959245681763, "hypothesis": "Escribí el número en el sobre. Léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "1eb4ddcffc3c129c028aac47e52860f69fb65fa241ce24535a725e374dd44a96", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dd3cd91d97026fd65e354d8934fdb5bad5e075de614304aebf0cc9072da64ccd", "generation_seconds_batch": 15.987734155962244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.998842239379883, "target_z": 1.7031249745289345, "ce": 6.149696350097656, "genuineness": 4.20609712600708, "identity": 0.5845401287078857, "hypothesis": "De deur, echt, de deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1eb4ddcffc3c129c028aac47e52860f69fb65fa241ce24535a725e374dd44a96.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": "1effc436ca90c9c17a75f0b2b9a17b9441b62456aeff0992b2a8f4a10305c856", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c2a241d5d4cd4691891ecb3ef3f15e7a81d58ea5dabf91d41c3b0e5a2a3776d", "generation_seconds_batch": 15.52198843297083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 6.348263263702393, "genuineness": 4.243753433227539, "identity": 0.6250503659248352, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1effc436ca90c9c17a75f0b2b9a17b9441b62456aeff0992b2a8f4a10305c856.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "1fcedbd643e0688da9c88fcfb3f3508e8b43e062a300774a07ae5048ae329843", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fd39adaf87dbb6ad52bc1600c397f2bc518847858a817cb8d92ae53b948710a0", "generation_seconds_batch": 14.769592819036916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6846208572387695, "target_z": 1.3593749724912492, "ce": 6.109982967376709, "genuineness": 4.394378662109375, "identity": 0.5279620885848999, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1fcedbd643e0688da9c88fcfb3f3508e8b43e062a300774a07ae5048ae329843.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": "1fecdcd1447095dccf2b934f3620f163a6c28026bfe1a44b9ce3867953949cf9", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "11911b7268d72489aefdc884445e30f6314b6769253bc129a48ff40e0f92b965", "generation_seconds_batch": 15.469603147008456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7988831996917725, "target_z": 1.484374996943472, "ce": 5.982900142669678, "genuineness": 4.174716949462891, "identity": 0.070073202252388, "hypothesis": "De sleutels liggen op de keukentafel. Ik ik in de la en daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/1fecdcd1447095dccf2b934f3620f163a6c28026bfe1a44b9ce3867953949cf9.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "209a628d119818888d43e087591e399d884c2b650893b1af44248b5bc67a451c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4e498b72517ba1ce2a709203668c8d7d02117796809e8d6c52799bcc30543e7a", "generation_seconds_batch": 19.857672200072557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.713186502456665, "target_z": 1.3906250438102328, "ce": 6.149696350097656, "genuineness": 4.055472373962402, "identity": 0.38459324836730957, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/209a628d119818888d43e087591e399d884c2b650893b1af44248b5bc67a451c.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": "20c78a3db48c5217f7bb97f107c5bf28ace8da3a6d6cc60f9ecacaa07a43d794", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "95b214e8cabdd75354198b44b020a7ed7d81de2c1906720b7fa3993faf33da76", "generation_seconds_batch": 20.756239845068194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7560348510742188, "target_z": 1.4375000203768524, "ce": 6.038498878479004, "genuineness": 4.268857479095459, "identity": 0.7625949382781982, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/20c78a3db48c5217f7bb97f107c5bf28ace8da3a6d6cc60f9ecacaa07a43d794.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "217e0ce1a38563bb08ab05bd8f69a5e7c59bd44c20e33ebd37b24206d3595b80", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3fbf63ceb992e2d56a803062d794c71922cbd25f04e760e379cd0af63c5e3abb", "generation_seconds_batch": 20.92242829303723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9845595359802246, "target_z": 1.6875000692812983, "ce": 6.213237762451172, "genuineness": 3.986435890197754, "identity": 0.09614955633878708, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/217e0ce1a38563bb08ab05bd8f69a5e7c59bd44c20e33ebd37b24206d3595b80.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": "21b3e6dbed1ae8c56a425be56fb19f997729c1963d84e57e9f43a077d2ecf12d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0edb0bb682d2deb10f6d37f3c26af4f4846b0f1deeebed62287dd984be7ddcc4", "generation_seconds_batch": 15.854753119056113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.891721248626709, "target_z": 1.5859374027005295, "ce": 6.0146708488464355, "genuineness": 3.9173994064331055, "identity": 0.5861575603485107, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/21b3e6dbed1ae8c56a425be56fb19f997729c1963d84e57e9f43a077d2ecf12d.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "22a1b0bba7832bcfd8e43e9980dd7e0a0114286a67644491fd1b4e73f1c3cf99", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "86bdb3c1db22e2b9f1a6baf5c75fb4be12c7e8a6f649f756b1005a3610eada51", "generation_seconds_batch": 22.51609367900528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120450735092163, "target_z": 0.7421875636776639, "ce": 6.197352409362793, "genuineness": 4.15588903427124, "identity": 0.1743192821741104, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het. Het stond naast het oude raam. We kunnen er samen.", "wer": 0.3333333333333333, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/22a1b0bba7832bcfd8e43e9980dd7e0a0114286a67644491fd1b4e73f1c3cf99.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "236d177f5a5b6866af3fe381600d8dee15ce10faf07608002dbb936430a30f3d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b1921b569d84ea02790eede626fe9ec217f5e485f32bf727067541ae2db8dabf", "generation_seconds_batch": 20.202797116944566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.484661817550659, "target_z": 1.140624994905787, "ce": 6.221180438995361, "genuineness": 4.111956596374512, "identity": 0.3650169372558594, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/236d177f5a5b6866af3fe381600d8dee15ce10faf07608002dbb936430a30f3d.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "23a696ac8c7c27afcdd0915477ca0e86a185ada7fadfc7e90638d72dcd89a875", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e0dbcf077c9b82f337fa8845683be841576ea8a4a02e44adf5b2bf006485864", "generation_seconds_batch": 23.56388650496956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.88457989692688, "target_z": 1.5781249500767116, "ce": 6.141753673553467, "genuineness": 4.18726921081543, "identity": 0.37946203351020813, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/23a696ac8c7c27afcdd0915477ca0e86a185ada7fadfc7e90638d72dcd89a875.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "23a732a30e99b420991d5eaf16b1d7f5e6c6f56851e38b087f148ee076954aea", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "613ad0756ab1c24efd8dee25c5afa44aa3122bfa66d3ca811c4b463196b4b112", "generation_seconds_batch": 19.34681889496278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7274692058563232, "target_z": 1.4062499490578688, "ce": 5.998785495758057, "genuineness": 4.168440818786621, "identity": 0.26410040259361267, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/23a732a30e99b420991d5eaf16b1d7f5e6c6f56851e38b087f148ee076954aea.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "23b698b88142c41ff3ccfb00f3407f749e39b53b4abd3e5b7dbfb74d94fcf3e8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80ae6fcda579f6292082475aa33ad04b56c7657b28edbd5b9353478ad4e4a47c", "generation_seconds_batch": 20.902788411010988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.656055450439453, "target_z": 1.3281251619959769, "ce": 5.816103935241699, "genuineness": 3.722842216491699, "identity": 0.06892283260822296, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/23b698b88142c41ff3ccfb00f3407f749e39b53b4abd3e5b7dbfb74d94fcf3e8.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "23ce677ae11e10841ad689569359920f128d589032e6782adfcbb42c79938372", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "744cfd0f7148b5621a72940b8b7ac4b1e79fa2423125d1407cf950a7e5fcad8d", "generation_seconds_batch": 15.872544825077057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.470378875732422, "target_z": 1.1249998288344394, "ce": 6.173524379730225, "genuineness": 3.898571252822876, "identity": 0.4767889976501465, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/23ce677ae11e10841ad689569359920f128d589032e6782adfcbb42c79938372.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "23dd13c1c501e9d3c5a8747b3aab1974ccedb76ce7483128d1e40136ae054058", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "edf7b88c7d6741d99db540b85ca7ce7ca9cdac894f4e8e1c18ee45d648408965", "generation_seconds_batch": 21.36969505401794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.834590196609497, "target_z": 1.5234375208862738, "ce": 5.998785495758057, "genuineness": 4.268857479095459, "identity": 0.7462996244430542, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/23dd13c1c501e9d3c5a8747b3aab1974ccedb76ce7483128d1e40136ae054058.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "23fc0d691ea3fb0fdfc5094f14cdcc5bf9595103d082c7c1061921b0bb458c7a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7fbd4e7342b8703e35edd1d3499398b4b5f46faee7c294ea7ff65eea165309e3", "generation_seconds_batch": 19.783948447089642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4418134689331055, "target_z": 1.0937500183391673, "ce": 6.062326908111572, "genuineness": 4.256305694580078, "identity": 0.4877549409866333, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/23fc0d691ea3fb0fdfc5094f14cdcc5bf9595103d082c7c1061921b0bb458c7a.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "241c5582cc39fc26ec6253f19097f03b85b02a53d95e8e46cd2efb8a62ee86e2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d951d0189914c652793c9c60709c3344701dab0fc6e0ab1372de0a677b6a43ab", "generation_seconds_batch": 21.987211835104972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.784395694732666, "target_z": 2.5624999796231474, "ce": 5.879645347595215, "genuineness": 4.15588903427124, "identity": 0.4613156020641327, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/241c5582cc39fc26ec6253f19097f03b85b02a53d95e8e46cd2efb8a62ee86e2.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": "24477653877e3787b9126b92ca26257c9230d8ed54c628e5820bba7cdb88ce9b", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Someone moved the little blue chair.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "70a73efb91c9daee72273d8147fe3627bf272a7c76e013ad331003ff17af370f", "generation_seconds_batch": 15.29444948094897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7274692058563232, "target_z": 1.4062499490578688, "ce": 6.348263263702393, "genuineness": 4.149612903594971, "identity": 0.5478452444076538, "hypothesis": "Someone moved the little blue chair. It used to stand here, beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/24477653877e3787b9126b92ca26257c9230d8ed54c628e5820bba7cdb88ce9b.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "24d98d6f588ffda86313fddb04b88cdf0887d30d025ab9815b147d88febe8d9f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1c83bc9e8260c76c1d61892da080090bb4c87c7c3e58c810b355313092b1dc4b", "generation_seconds_batch": 23.63954745500814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.955993890762329, "target_z": 1.6562499979623146, "ce": 6.078212261199951, "genuineness": 4.18099308013916, "identity": 0.5541951656341553, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/24d98d6f588ffda86313fddb04b88cdf0887d30d025ab9815b147d88febe8d9f.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "26426f6aa2dbee92712d30d945f16a2e3bf895bc1aecc9c768ec6a48516c43ce", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "80acd9ba7d7872620aea65ce24a17129bd16e9435d260839bf8a0b340bb2bf0e", "generation_seconds_batch": 20.25487637508195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.009758949279785, "target_z": 0.6210936351254943, "ce": 6.459460258483887, "genuineness": 4.287685871124268, "identity": 0.2855277359485626, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/26426f6aa2dbee92712d30d945f16a2e3bf895bc1aecc9c768ec6a48516c43ce.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "26479158efc31847c5ea81c6598f60b680d1a4b9afcd0aaecca529d62ec615ef", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "487b4a743c8c6d110c09123f1f99fca485d15f01537c5585a0e4baa3e725dee0", "generation_seconds_batch": 20.563740335055627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.198801279067993, "target_z": 1.9218749521143967, "ce": 6.125868320465088, "genuineness": 4.494794845581055, "identity": 0.6540577411651611, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/26479158efc31847c5ea81c6598f60b680d1a4b9afcd0aaecca529d62ec615ef.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "268da077865a76228c442f912822256ee925fada2bf7be9cc6ea9064ade52e06", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0d361daa1c29f94b9c6a417a82546062c66af9dd004d6e404f093bd6d471b84c", "generation_seconds_batch": 15.174614883959293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.463237762451172, "target_z": 1.1171876370343328, "ce": 6.252951145172119, "genuineness": 4.20609712600708, "identity": 0.6904579401016235, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/268da077865a76228c442f912822256ee925fada2bf7be9cc6ea9064ade52e06.mp3" }, { "id": "heldout-en-1", "language": "en", "sentences": [ "The keys are on the kitchen table.", "I checked the drawer... then looked beside the window.", "Take them with you when you leave." ], "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-1", "key": "26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Intense Interest. 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": "5b9833feb4f8b2d2d0370e218e6c3986d1e7b1183be86c5e91600be6eb29766e", "generation_seconds_batch": 17.729181260918267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2061474323272705, "target_z": 0.8359375168109032, "ce": 6.348263263702393, "genuineness": 4.507347106933594, "identity": 0.24281978607177734, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "273afe890aac18f701216f816039147e74d0fc5ca1c80927bd9e400da45c45f9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ce9d1c8178679438a7c17961d375e5ebefbc5ddbbb384113bf684ffb879a16fc", "generation_seconds_batch": 21.42066722898744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0954556465148926, "target_z": 0.7148435882587337, "ce": 6.165581703186035, "genuineness": 3.886019229888916, "identity": 0.21092364192008972, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/273afe890aac18f701216f816039147e74d0fc5ca1c80927bd9e400da45c45f9.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "27593bceb27465522ea76feaacb9821c1d1184bad864d3f5eb5b3cec21a24c35", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ec8b07a8a8b4677c11200a30ff2e54392957863b68c4c375e8521be40c0d8ac5", "generation_seconds_batch": 16.54666788794566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9845595359802246, "target_z": 1.6875000692812983, "ce": 6.141753673553467, "genuineness": 4.21237325668335, "identity": 0.4054338335990906, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/27593bceb27465522ea76feaacb9821c1d1184bad864d3f5eb5b3cec21a24c35.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "2818d0022af1c20f2ae9b1f7705fc59887a4696b1afe38a13f781ef0392bac5f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "74688418ff4b9db5a5fd6bb728d940d97e0cb50d7cece081c5d5094d97e78ce9", "generation_seconds_batch": 20.84375582600478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4560961723327637, "target_z": 1.1093749235868033, "ce": 6.443574905395508, "genuineness": 4.281409740447998, "identity": 0.5862613320350647, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/2818d0022af1c20f2ae9b1f7705fc59887a4696b1afe38a13f781ef0392bac5f.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "28a0ed55ebba6510d7348828e5a52db6fc0ff7b3e9305dbdae75e5b8d936ce2a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a50e23ec709cdbf60e7b7c83e491758dc9b76f8781e58ba86f033148826c944b", "generation_seconds_batch": 15.330219108029269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 6.348263263702393, "genuineness": 3.9173994064331055, "identity": 0.48869219422340393, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/28a0ed55ebba6510d7348828e5a52db6fc0ff7b3e9305dbdae75e5b8d936ce2a.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "28c3fa2d87ce4d613ad8d931fbf6b25e96c7cfca0f8f4db2c08bf0c2ca80c5ea", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f2f1ece4b37763c814f1c39d34e11d11d6a32511782f89374c5b833e8c7baddc", "generation_seconds_batch": 20.811868298915215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4346721172332764, "target_z": 1.0859375657153492, "ce": 6.197352409362793, "genuineness": 4.319066047668457, "identity": 0.3648194670677185, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/28c3fa2d87ce4d613ad8d931fbf6b25e96c7cfca0f8f4db2c08bf0c2ca80c5ea.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "28db4203156865b9fc0ab0172b45c574c639d7d4d4e3c679160411e4c9df23a8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b69f15b6df89e204437298a8685f9f493e3edee052979f3bb4c9853c667cbac7", "generation_seconds_batch": 22.4887583340751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.955993890762329, "target_z": 1.6562499979623146, "ce": 6.332377910614014, "genuineness": 4.143336772918701, "identity": 0.517824649810791, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/28db4203156865b9fc0ab0172b45c574c639d7d4d4e3c679160411e4c9df23a8.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "28e158ed24b344925a038ec590a411e86823e9ee5d2024e7554d26ed99310192", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "520a8bc93699db3e94b28e0204403a5639705cf152f5aad1a992735f57a00590", "generation_seconds_batch": 21.42066722898744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.352545976638794, "target_z": 0.9960937084821632, "ce": 6.197352409362793, "genuineness": 3.7667744159698486, "identity": 0.3410043716430664, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/28e158ed24b344925a038ec590a411e86823e9ee5d2024e7554d26ed99310192.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "28eb3f67fe6d5a158386b9ffe4680e58ef7de45acd6d767ff56fb6c9eed0ea9c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "17079505494b24da4353ddbced1ce53d2e2dc6e1733ca47a3df738a8db48da69", "generation_seconds_batch": 20.416274357005022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.598924160003662, "target_z": 1.2656250193580099, "ce": 6.38797664642334, "genuineness": 4.149612903594971, "identity": 0.19279108941555023, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/28eb3f67fe6d5a158386b9ffe4680e58ef7de45acd6d767ff56fb6c9eed0ea9c.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "290cf9712927f5d7f519a21a587e5043b692131033f4b694cbd66cbdb45613db", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2060b6512d320692815043fab65dd412510a59b63369d07bbbad738beeb26bd2", "generation_seconds_batch": 20.96784788405057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.591782569885254, "target_z": 1.2578123059104804, "ce": 5.80021858215332, "genuineness": 4.149612903594971, "identity": 0.5114325284957886, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/290cf9712927f5d7f519a21a587e5043b692131033f4b694cbd66cbdb45613db.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "293010bf45668b02787444757a736d0244e0910af78290d05c2ce0a5d133e3d6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b9e7b951045518041f3fb015dcb481605db5ccf162379090aa1ffd83222d0598", "generation_seconds_batch": 20.489954328979366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.313063621520996, "target_z": 2.04687497656662, "ce": 6.324435234069824, "genuineness": 4.381826400756836, "identity": 0.5976020097732544, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/293010bf45668b02787444757a736d0244e0910af78290d05c2ce0a5d133e3d6.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "296beab062cd1100e3d40be1990adb303c87afce1f95e1eac69009a93971ecca", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "23b9f9fe8c6eabeb7294debbeeb1625a0e96ccd648ef7933300b020ade27dcbe", "generation_seconds_batch": 16.76758820109535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7488932609558105, "target_z": 1.429687306929323, "ce": 6.149696350097656, "genuineness": 4.105680465698242, "identity": 0.483527809381485, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/296beab062cd1100e3d40be1990adb303c87afce1f95e1eac69009a93971ecca.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "29ac61e6509ffec9fd8c576960e4b4b256a895e5e13971c3587bee6a4dd4c887", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7745c1ee94d4b1db5dda9da340d66e973b5b22bdc0fa3001ecbd5fffeeb15bf9", "generation_seconds_batch": 23.581020860001445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9919055700302124, "target_z": 0.6015625035659492, "ce": 6.133810997009277, "genuineness": 4.030367851257324, "identity": 0.6241670250892639, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/29ac61e6509ffec9fd8c576960e4b4b256a895e5e13971c3587bee6a4dd4c887.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "2a545894eef20fba62fcf469de09a982bb8fd3e440d8371a929a58910686d4b3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "398e132f01c633364ade3c4577db499aa8ea4331f242565e5f11d72cae2a74f3", "generation_seconds_batch": 21.258628226001747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.584641456604004, "target_z": 1.2500001141103736, "ce": 6.141753673553467, "genuineness": 4.381826400756836, "identity": 0.7219897508621216, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/2a545894eef20fba62fcf469de09a982bb8fd3e440d8371a929a58910686d4b3.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "2aa3cf9c2a04645f8afe37804a5e9bba0b9dfa7e2e9d1259bd194515072d10f1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3dd484c060aeb46f48aeb603f5676e72fab1fb02110d408ff79a077532698ae7", "generation_seconds_batch": 20.721114468062297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1525869369506836, "target_z": 0.7773437308967008, "ce": 6.284721851348877, "genuineness": 4.300237655639648, "identity": 0.7622504830360413, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/2aa3cf9c2a04645f8afe37804a5e9bba0b9dfa7e2e9d1259bd194515072d10f1.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "2b45b88c172f48d205b3bbc5d26de6a761bc20d4cea74bc260b310a1ca16c131", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8bb7bb4647352733a2991b52508fbc0dd97c1a2d4c3bb829791d1bf0af1ac4d7", "generation_seconds_batch": 21.824025996029377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6132068634033203, "target_z": 1.281249924605646, "ce": 6.038498878479004, "genuineness": 4.457139015197754, "identity": 0.3859444856643677, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/2b45b88c172f48d205b3bbc5d26de6a761bc20d4cea74bc260b310a1ca16c131.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": "2b5dbc081d0c119aa35be09c7c1cda0915e969dfab7d0c74bfdb903c97e52e69", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83012d88d94fca730d8a46bb12918c811a1b35271783e88c5ffa965cab415e25", "generation_seconds_batch": 15.329538458958268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.88457989692688, "target_z": 1.5781249500767116, "ce": 6.38003396987915, "genuineness": 4.287685871124268, "identity": 0.2218950390815735, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/2b5dbc081d0c119aa35be09c7c1cda0915e969dfab7d0c74bfdb903c97e52e69.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "2c8f9b6876d18a9d096cf7d62c64d9f6181554d0646c1c38e67058bf503387e6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1a5294cd97db41e4d842471468d7a88e11f8e42c107b2b7796ad4b43a87a520f", "generation_seconds_batch": 20.30470326996874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.777459144592285, "target_z": 1.460937639072018, "ce": 6.268836498260498, "genuineness": 4.3127899169921875, "identity": 0.3590770363807678, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/2c8f9b6876d18a9d096cf7d62c64d9f6181554d0646c1c38e67058bf503387e6.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "2ce2f797d1d29fc9799904ad6b22dde682317a9d4904d2cf8ea8cf2af884cbcd", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a0ac752c42ccba93a5dc4bf5017019c587f3d0186ad1d1cb6ac93863bd5e4a01", "generation_seconds_batch": 20.27051696192939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2130842208862305, "target_z": 1.937500118185744, "ce": 6.252951145172119, "genuineness": 4.344170093536377, "identity": 0.373323917388916, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/2ce2f797d1d29fc9799904ad6b22dde682317a9d4904d2cf8ea8cf2af884cbcd.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": "2d8fa56c9d818a3d175f8908272ea3c64469488281653dfec67259ad9ece9f30", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9db3ec67d18130e0dcf7e8f5b53d72ba6eecebb7551c137bcec7351528c35a47", "generation_seconds_batch": 15.522001776960678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4418134689331055, "target_z": 1.0937500183391673, "ce": 6.181467056274414, "genuineness": 4.419482707977295, "identity": 0.6449514627456665, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/2d8fa56c9d818a3d175f8908272ea3c64469488281653dfec67259ad9ece9f30.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "2fcf8b9e1ef3f96bf7e6677f1beb81bec1c4866b2cce0dfbdbce502e69194381", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e28d095a526161bfbc3d31603ef635c4fd16aa901b47bccca382ce697e5dd933", "generation_seconds_batch": 23.348749800934456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.234713077545166, "target_z": 0.8671875881298868, "ce": 6.2767791748046875, "genuineness": 4.231201171875, "identity": 0.7073312401771545, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/2fcf8b9e1ef3f96bf7e6677f1beb81bec1c4866b2cce0dfbdbce502e69194381.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "2ff7718a1538b4e3a46992dff70d005e6d14cc3dd7089efc4dd15d868c2a91d7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d476d641344b571b6813479c4dc1a66774d38c366fc4d090e21971f2ccb3d7c6", "generation_seconds_batch": 17.859765148954466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2630739212036133, "target_z": 1.9921875473761819, "ce": 5.967014789581299, "genuineness": 4.231201171875, "identity": 0.7427694797515869, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/2ff7718a1538b4e3a46992dff70d005e6d14cc3dd7089efc4dd15d868c2a91d7.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "3020ce1297b13de54689794ce12c973f1391e7bcdcc853717ab60a6db2bbe290", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e4e58b1a613d27e867a4ecf1ea5cbad83bab28d9033a6023ee70c762b9bdcf64", "generation_seconds_batch": 17.574152011075057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.534651756286621, "target_z": 1.195312684919936, "ce": 6.435632705688477, "genuineness": 4.319066047668457, "identity": 0.3506678342819214, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3020ce1297b13de54689794ce12c973f1391e7bcdcc853717ab60a6db2bbe290.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "30262df59627ea7a4b1f32b7a347ffeb4195aeb9665d36959e06df9c234bd1d8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "170e8c695fa31e5969aad898dede13df5e109b801e63afd47ce9da68f6f5969e", "generation_seconds_batch": 20.329823613050394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 6.205295085906982, "genuineness": 3.8420867919921875, "identity": 0.3620678782463074, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/30262df59627ea7a4b1f32b7a347ffeb4195aeb9665d36959e06df9c234bd1d8.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": "307c67176beb2ef84689c7e584fae04d89d89991b87d69940720b87867e211dd", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7712c8d222e281ac0535b05d491fc31c30fb3e34be1da10f6572644d45e741a", "generation_seconds_batch": 17.303050674963742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.006728172302246, "genuineness": 4.7332844734191895, "identity": 0.7793586850166321, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/307c67176beb2ef84689c7e584fae04d89d89991b87d69940720b87867e211dd.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "30e0586b43b91223d7bc7f647732ce0ba0b23263f7fa6de2a7ddef81f46b0d57", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c29c6bc62e10a1324f5838a4ac954faca0f321872922b4228c99e2649fc4f54e", "generation_seconds_batch": 19.756566883064806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.013124942779541, "target_z": 1.7187498797765706, "ce": 5.903473377227783, "genuineness": 4.419482707977295, "identity": 0.636857271194458, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/30e0586b43b91223d7bc7f647732ce0ba0b23263f7fa6de2a7ddef81f46b0d57.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": "311133469b0e8bd2e717f9cf8e9dec9c795aa64c5bb020843688b57bb91996a1", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6581835d87113077c331fdffa0ac51ad4ec6d0e91a81050453aea1a25c7777b1", "generation_seconds_batch": 17.033917936962098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.013124942779541, "target_z": 1.7187498797765706, "ce": 5.967014789581299, "genuineness": 3.9550557136535645, "identity": 0.5969846248626709, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/311133469b0e8bd2e717f9cf8e9dec9c795aa64c5bb020843688b57bb91996a1.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "31950db1f02048268559a9cab4a05bb8394d0d2987d4cba24d66a40bc987e6e5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c517c13d14f61ff22686cfe33c0b058d203fb311d028ec3d4dce4e01891fe6ae", "generation_seconds_batch": 20.86182191304397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.288273334503174, "target_z": 0.9257811132203779, "ce": 6.332377910614014, "genuineness": 4.218649387359619, "identity": 0.36826199293136597, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/31950db1f02048268559a9cab4a05bb8394d0d2987d4cba24d66a40bc987e6e5.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "319bc5630de139c88ed26c8332c6e258d5e195a36f3c5d82cf0e6516d8f53418", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "835a6b30f2923ba3e7a5cc2d7d861190385989af9d70c870a0cec3d468221cd0", "generation_seconds_batch": 15.042259083944373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3846821784973145, "target_z": 1.0312498757012, "ce": 5.5738525390625, "genuineness": 3.9173994064331055, "identity": 0.5584427118301392, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/319bc5630de139c88ed26c8332c6e258d5e195a36f3c5d82cf0e6516d8f53418.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "32990f1e87feb02c154415c9319d7ace9a2b9cd271109c9eb19a25b5836b62b2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e11e3407bc21a4ccd10ff194da698760765e024bf23461e5750b55c39e1b5059", "generation_seconds_batch": 16.885390685056336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7988831996917725, "target_z": 1.484374996943472, "ce": 6.213237762451172, "genuineness": 4.457139015197754, "identity": 0.32959702610969543, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/32990f1e87feb02c154415c9319d7ace9a2b9cd271109c9eb19a25b5836b62b2.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "33045bc11a459793f8c1f64fd853d7ec0cdfe831c21950ab26ab9bfb02fb4b04", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "904002e5fe4574ba12a6e4647a28129b3264037a875402e78575bf3fbe755f33", "generation_seconds_batch": 23.912906158948317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.934569835662842, "target_z": 1.6328126400908605, "ce": 6.268836498260498, "genuineness": 4.1998209953308105, "identity": 0.23071366548538208, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/33045bc11a459793f8c1f64fd853d7ec0cdfe831c21950ab26ab9bfb02fb4b04.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "330bb0835c4d20f5915f38b3d7705a2f6b23ea70557da6a0d029270ebd4627eb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0243fd1ce91b7203469de5e7e967c3019e538bf99efe81158463e19a8161e02e", "generation_seconds_batch": 15.25920651294291, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.713186502456665, "target_z": 1.3906250438102328, "ce": 6.260893821716309, "genuineness": 4.243753433227539, "identity": 0.665894091129303, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/330bb0835c4d20f5915f38b3d7705a2f6b23ea70557da6a0d029270ebd4627eb.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": "3318a2c4a98f3e6c282962207639cf3f10588609a32c0591c21994f3fc39757c", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The road turns left behind the bridge.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c6aed8a715833ff7b5986cb00d1428b3a86aadbbdf6d6884fec520ae1347f3e3", "generation_seconds_batch": 15.524767274037004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6274895668029785, "target_z": 1.2968748298532822, "ce": 6.356205940246582, "genuineness": 3.9425034523010254, "identity": 0.5059683322906494, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3318a2c4a98f3e6c282962207639cf3f10588609a32c0591c21994f3fc39757c.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "33376e50f97b0d0658ed0adf5dfaaa5e8136a1dd17df8f6dfa3065626cb6bf5f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "985ddbfc96853313dd03ce413e133ad9f277d2ad7fc920f4edd1a9bd443adf4b", "generation_seconds_batch": 21.824025996029377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.784600257873535, "target_z": 1.4687498308721247, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.6821386218070984, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/33376e50f97b0d0658ed0adf5dfaaa5e8136a1dd17df8f6dfa3065626cb6bf5f.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "335c156c5367d3412c3033126139d258c7c336a14b42d0cf7a60d7cb766dcc54", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5b531d4dbcd1edb226109ebc43ae30c8a3de21557a21ddc3f8a5b818594148ae", "generation_seconds_batch": 20.540664230939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6741135120391846, "target_z": 0.2539062752163549, "ce": 6.348263263702393, "genuineness": 4.7081804275512695, "identity": 0.6494714021682739, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/335c156c5367d3412c3033126139d258c7c336a14b42d0cf7a60d7cb766dcc54.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "3392496593e0e237c367cdbadb8ff3c0eaf34b7c141ecdee7a34c1f66fc6dbf3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "73b2620d539bb1ea6282d040c7f1f565321c84138a03fc8385860b422b1ed624", "generation_seconds_batch": 20.209604447009042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.163299083709717, "target_z": 0.7890625402442836, "ce": 6.24500846862793, "genuineness": 4.469690799713135, "identity": 0.4566614627838135, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3392496593e0e237c367cdbadb8ff3c0eaf34b7c141ecdee7a34c1f66fc6dbf3.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "339c2368cf69cad9c07cdcb639fb0bf3e2a4fe31ea4e0cc98f52a225fe5308bc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "23064c188184f4797bfb914cb4cb0a435154258c2067cdec861208a927193a9d", "generation_seconds_batch": 19.938471393077634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0918850898742676, "target_z": 0.7109374923586803, "ce": 6.1894097328186035, "genuineness": 4.557555198669434, "identity": 0.6023526191711426, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/339c2368cf69cad9c07cdcb639fb0bf3e2a4fe31ea4e0cc98f52a225fe5308bc.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "33b9a39f9d03c3b108e794eae49490347f00a33180e033fe5a5c641e892532b3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0f3d36b24b007c5571d95d760b0cf85bcb45d4d01fc6d09288dc482eb504c853", "generation_seconds_batch": 20.64773129997775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9274282455444336, "target_z": 1.6249999266433313, "ce": 5.25614595413208, "genuineness": 3.600459337234497, "identity": 0.4445042014122009, "hypothesis": "The door is still open! I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/33b9a39f9d03c3b108e794eae49490347f00a33180e033fe5a5c641e892532b3.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "33ddeec97fa7b88d946c5eaac1b77a0b8eb0871811357b7b5d2f6edc176c1942", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5b7436b0cb46c421729f234bc3365de7fc7d623069c3e9f0008b5da5cc783818", "generation_seconds_batch": 21.406646671006456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.955993890762329, "target_z": 1.6562499979623146, "ce": 6.340320587158203, "genuineness": 4.3127899169921875, "identity": 0.6580865979194641, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/33ddeec97fa7b88d946c5eaac1b77a0b8eb0871811357b7b5d2f6edc176c1942.mp3" }, { "id": "heldout-nl-2", "language": "nl", "sentences": [ "De weg gaat linksaf na de brug.", "Loop verder... tot aan het kleine houten hek.", "Ik wacht aan de andere kant." ], "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-2", "key": "33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Intense Interest. 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": "578bf830502fdac3700391e614a570b41ad2cc306cb18a414a0364ee06b7cefd", "generation_seconds_batch": 15.506036958075128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3096976280212402, "target_z": 0.9492187319155434, "ce": 6.197352409362793, "genuineness": 4.356721878051758, "identity": 0.8430875539779663, "hypothesis": "De weg gaat linksaf na de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.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": "340681128b74a2bcea897ffdce82b0e320a08548c5629ff8b7909d8e6c49ba8f", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9560cda29f12c31af23a47b3a3ab0ad931a5386eaf38c0eb39da179be0f7206", "generation_seconds_batch": 17.393045912962407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1630945205688477, "target_z": 1.8828126889953065, "ce": 6.1894097328186035, "genuineness": 4.268857479095459, "identity": 0.6448675990104675, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guarté el teléfono. Dime cuándo podemos hablar.", "wer": 0.05, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/340681128b74a2bcea897ffdce82b0e320a08548c5629ff8b7909d8e6c49ba8f.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "345b082000c288bf8ea9e573f62ea8405bbb680ecccc7986d9f0bf97bbf072ee", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "34afb6515d4386ce359030a693c1acdcc0bf3662104ae3488e7dcb712958de48", "generation_seconds_batch": 15.332236928050406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 5.728734970092773, "genuineness": 4.099404335021973, "identity": 0.6282788515090942, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/345b082000c288bf8ea9e573f62ea8405bbb680ecccc7986d9f0bf97bbf072ee.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Intense Interest. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "cc0a5a3b7a5fab24e383600a645fc292d31882b575eec3eb8a2b229750f58b34", "generation_seconds_batch": 16.25422698399052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8972821235656738, "target_z": 0.4980469194470094, "ce": 6.4912309646606445, "genuineness": 4.168440818786621, "identity": 0.3590507507324219, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.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": "34da31d1504f6fce15472b79b9ca5023fed3c08bdd4ee61a7917126dc31bc42c", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I wrote the number on the envelope.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "03630d98bb9b31ab269791f739ffb282259ed2d472b4930a31e4fee8ca6287a7", "generation_seconds_batch": 15.26228989311494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5703585147857666, "target_z": 1.2343749480390263, "ce": 6.268836498260498, "genuineness": 3.747946262359619, "identity": 0.6076931357383728, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/34da31d1504f6fce15472b79b9ca5023fed3c08bdd4ee61a7917126dc31bc42c.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "34f526cbddde231041161cf47cb65165cf601131fca96316f3aadd9071fa261a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e7ac0ecea55d30f9b640ac9b304e329a9235be00eb97cc9a16edc6b304c70b70", "generation_seconds_batch": 20.802370153018273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0883145332336426, "target_z": 0.7070313964586269, "ce": 6.284721851348877, "genuineness": 4.557555198669434, "identity": 0.6557407379150391, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/34f526cbddde231041161cf47cb65165cf601131fca96316f3aadd9071fa261a.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": "35ac903f1e11168c26a1e814b69859f9df31ceb86bf43748b97566032d63c58d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a1726acd8af3ab51e59c5dda43c16d9ad4501fb13b15da833897aa1d1024b60", "generation_seconds_batch": 15.351007401011884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.34897518157959, "target_z": 0.9921873517583985, "ce": 6.459460258483887, "genuineness": 4.168440818786621, "identity": 0.47061651945114136, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/35ac903f1e11168c26a1e814b69859f9df31ceb86bf43748b97566032d63c58d.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "35f4e82db3a9315fafd9fa58cccb03db4bf2bc8d06bf654515dbcc82985e016a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "58d348428934e8faa3e4965cadaaee0427494de1d3543e62cad4730e353c33c7", "generation_seconds_batch": 16.208718682988547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0488319396972656, "target_z": 1.7578124037193723, "ce": 5.9431867599487305, "genuineness": 3.7918784618377686, "identity": 0.5011935234069824, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/35f4e82db3a9315fafd9fa58cccb03db4bf2bc8d06bf654515dbcc82985e016a.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": "3602225c81891a47b6ccaa02938ec8651254dc507a7a4ba8d2b604aee8394f01", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3c0b16cc481679593c238d809fee5fb250704cbf99eb044817fa964e2cbc98b3", "generation_seconds_batch": 15.409346689004451, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.656055450439453, "target_z": 1.3281251619959769, "ce": 6.403861999511719, "genuineness": 4.532451152801514, "identity": 0.5518456697463989, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier, neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3602225c81891a47b6ccaa02938ec8651254dc507a7a4ba8d2b604aee8394f01.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": "360a8bf6efae9be404dc658be203250ac1ec915f7c97d29a6e2e29dff8b1da81", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f13ef9b5c3c73c16ed6c2b0187c73330785330a1cc59e7029caaf3a032d76ef5", "generation_seconds_batch": 14.860916550969705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.120245933532715, "target_z": 1.8359374516049753, "ce": 6.141753673553467, "genuineness": 4.137060642242432, "identity": 0.5432215929031372, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/360a8bf6efae9be404dc658be203250ac1ec915f7c97d29a6e2e29dff8b1da81.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "36134209059323172a9a0bb7048c9627d9a3167a9cc49c36ed18b2e78a0311aa", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "535137b960a9b3da7b55a497e983f20f97cd51e5806a63d5c12b8c463d0224e0", "generation_seconds_batch": 19.731795337051153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8488731384277344, "target_z": 1.5390626869576212, "ce": 6.117925643920898, "genuineness": 3.948779582977295, "identity": 0.768016517162323, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/36134209059323172a9a0bb7048c9627d9a3167a9cc49c36ed18b2e78a0311aa.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "36a360ae5fc302f54f1f7a432b7261e18ad4f40fbc6375e9b8b89f742f32baeb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e59e9771dc4989ecfcfe2caff008f442a23e2d8b02621341289e03d7e75d02fa", "generation_seconds_batch": 22.45881299697794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.070256233215332, "target_z": 1.7812500224145378, "ce": 6.229123115539551, "genuineness": 4.137060642242432, "identity": 0.4369005262851715, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/36a360ae5fc302f54f1f7a432b7261e18ad4f40fbc6375e9b8b89f742f32baeb.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "376fb05501a3e70fc4eea6cfa533efa11fac318a8119f353aca62b83cb67a3bc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "be6ff51778fd94a653d1a0ef51eab9caa5b8a691d46a6d8823095fcce655339c", "generation_seconds_batch": 20.770266088075005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3168389797210693, "target_z": 0.9570311845393615, "ce": 6.268836498260498, "genuineness": 4.457139015197754, "identity": 0.6018104553222656, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/376fb05501a3e70fc4eea6cfa533efa11fac318a8119f353aca62b83cb67a3bc.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "389a82267221a5c06605c640ff91fdd69a97a82acc888f439cb7ecf650ed5941", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a0b3ff9219528e03a3ab989c59b5b96dbc3a5852a7f20e4f75863ea375773b9", "generation_seconds_batch": 21.910660989000462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8558096885681152, "target_z": 2.640625027508751, "ce": 5.839932441711426, "genuineness": 4.118232727050781, "identity": 0.6230272054672241, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/389a82267221a5c06605c640ff91fdd69a97a82acc888f439cb7ecf650ed5941.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "38fff5b7ee1ca81e028fec241fca13ada64ffdfe046cadb4bbfabc42105bd2ed", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "75ff090af8978df7fe36a0b08d9ab4590da3ce7d7d37749aa58496d6c00e4d67", "generation_seconds_batch": 15.174614883959293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1525869369506836, "target_z": 0.7773437308967008, "ce": 6.205295085906982, "genuineness": 4.444586753845215, "identity": 0.6308305859565735, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/38fff5b7ee1ca81e028fec241fca13ada64ffdfe046cadb4bbfabc42105bd2ed.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "39338b0ca63aeda6e42bfdf15ef53c18f13e9bcd74179ada71be733ea75cd211", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e7e76e9db086d8c05aa619250885f521098413b081821a22274fdf9d4a8adf1f", "generation_seconds_batch": 19.99320493999403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2273669242858887, "target_z": 1.9531250234333803, "ce": 5.784333229064941, "genuineness": 4.049196243286133, "identity": 0.4811883866786957, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/39338b0ca63aeda6e42bfdf15ef53c18f13e9bcd74179ada71be733ea75cd211.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "39359b76dc014ad28b06e685e139820cde80ac25abb03a6b068d095951c4220c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3de746ee07d61dcca6bb1af3ec4284a158aef7bcb22ad39097ccffb8877428c1", "generation_seconds_batch": 20.766324033029377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.656055450439453, "target_z": 1.3281251619959769, "ce": 6.0146708488464355, "genuineness": 4.720732688903809, "identity": 0.5953223705291748, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/39359b76dc014ad28b06e685e139820cde80ac25abb03a6b068d095951c4220c.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "39906e931cf23849feb1cf0d64b203eb7af412813a05c8dcbe49df283477faa8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6d78b8ba5b0744d90dac29024ae112944f7346f40a2f640f77c8d43452bb40fe", "generation_seconds_batch": 22.029708410962485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6415677070617676, "target_z": 2.4062498838519413, "ce": 5.5817952156066895, "genuineness": 4.306513786315918, "identity": 0.5823661684989929, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/39906e931cf23849feb1cf0d64b203eb7af412813a05c8dcbe49df283477faa8.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "39989585f944f44c5b01a9308b24e84e17a44e7e5c58575671427a99c0c377af", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cf8cebb94977c6eccdb6b1e6a4b7aaaa2eafe6ecbecb460f7d957453c396c026", "generation_seconds_batch": 26.57848693896085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9490572214126587, "target_z": 0.5546875269993294, "ce": 6.109982967376709, "genuineness": 4.507347106933594, "identity": 0.6503052711486816, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/39989585f944f44c5b01a9308b24e84e17a44e7e5c58575671427a99c0c377af.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "3a55ac9debca3b1bfa7c1d501f43ff08ce7d7be7efb679074a85d14c9d244a0f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "abc931eec1b8f9a6cf4d43860e8ef778ba6f14aef9e931465b89d513fb01dc73", "generation_seconds_batch": 21.00152736599557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0847437381744385, "target_z": 0.7031250397348623, "ce": 6.125868320465088, "genuineness": 4.149612903594971, "identity": 0.6651595830917358, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3a55ac9debca3b1bfa7c1d501f43ff08ce7d7be7efb679074a85d14c9d244a0f.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "3afbb664913be30270c62e91f582bbbacdde970057a90d74ab5645e3b962e684", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5b1d93a5bbf5c0fc110eb87722d784166c34fdc920f7db9b2a28ad1b382819a6", "generation_seconds_batch": 20.858991027926095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 6.300607204437256, "genuineness": 4.482243061065674, "identity": 0.3758500814437866, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3afbb664913be30270c62e91f582bbbacdde970057a90d74ab5645e3b962e684.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "3b35d32ed252cbf2682b860983fcf4302ede7fe162a3b3f0c2a14e1c870533e4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "77eccba598acf4c8cce9ef775a6b98a0fa1131c195e132be7855297611bdf8d9", "generation_seconds_batch": 23.434664042084478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7274692058563232, "target_z": 1.4062499490578688, "ce": 5.8875885009765625, "genuineness": 4.287685871124268, "identity": 0.5504421591758728, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3b35d32ed252cbf2682b860983fcf4302ede7fe162a3b3f0c2a14e1c870533e4.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "3bccae66428203b459dcb344ca38b915fe1dbeb39aef5f29abe73681f0e63f37", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a4f81713ab0c8a9bfd01f084618e399bb25abb57885537f121679a9a7f4e1987", "generation_seconds_batch": 20.15202535991557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5060858726501465, "target_z": 1.1640623527772411, "ce": 6.038498878479004, "genuineness": 4.3127899169921875, "identity": 0.5634142160415649, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3bccae66428203b459dcb344ca38b915fe1dbeb39aef5f29abe73681f0e63f37.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "3be776f2aa29a5277f935c9d6cda4e705dee226751375fbf5c11fb1d47376bea", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0bb08f9898a8aec144d311fe600534678fd8fc1cf21b912d4b5ef727b5dcb94b", "generation_seconds_batch": 20.766756149940193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.841526985168457, "target_z": 2.6250001222611146, "ce": 6.022613525390625, "genuineness": 3.9425034523010254, "identity": 0.568572461605072, "hypothesis": "I found the little box! It was beside the old window! We can look inside together!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3be776f2aa29a5277f935c9d6cda4e705dee226751375fbf5c11fb1d47376bea.mp3" }, { "id": "heldout-nl-1", "language": "nl", "sentences": [ "De sleutels liggen op de keukentafel.", "Ik keek in de la... en daarna naast het raam.", "Neem ze mee als je weggaat." ], "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-1", "key": "3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Intense Interest. 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": "0d57388050b38e1dc03c6e421d9b50448cac86ef687675dedd675f63ff2213bc", "generation_seconds_batch": 16.859554570983164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.238283634185791, "target_z": 0.8710936840299403, "ce": 6.252951145172119, "genuineness": 4.243753433227539, "identity": 0.6175240278244019, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.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": "3cbf59ab5be6956c3b0015b7403513a8eb17eb456d739b06427d942dc8e26a16", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Escribí el número en el sobre.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4931c119d1543f3df14df0a5578569df228aa98c2b5e64e98ae99546e27f0b00", "generation_seconds_batch": 20.705657041980885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7346105575561523, "target_z": 1.414062401681687, "ce": 6.0305562019348145, "genuineness": 4.168440818786621, "identity": 0.38362085819244385, "hypothesis": "Escribí el número en el sobre, léelo bien, y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3cbf59ab5be6956c3b0015b7403513a8eb17eb456d739b06427d942dc8e26a16.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": "3e890aafaf04d0965f515155d6fa1f2a84b40a688b86d83b5b0b5fa63020f0ef", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a2ee5945ae84f14451f297bc587618928dc937d3b0c029b0ecf8fcfd1c28570f", "generation_seconds_batch": 20.734128348063678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8488731384277344, "target_z": 1.5390626869576212, "ce": 6.054384231567383, "genuineness": 3.9173994064331055, "identity": 0.5855922102928162, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3e890aafaf04d0965f515155d6fa1f2a84b40a688b86d83b5b0b5fa63020f0ef.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": "3f7388f6f14ddddaa3bbeb88ac6c02cdbed1861eb638fdd33bff873f01af21ed", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I wrote the number on the envelope.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f38e59e215e2afd792ceb12d1f1f170750e1540ba14fe08f6f9047e0b77adc93", "generation_seconds_batch": 15.36887896899134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.248995780944824, "target_z": 0.882812493377523, "ce": 6.38003396987915, "genuineness": 3.7667744159698486, "identity": 0.3060510754585266, "hypothesis": "I wrote the number on the envelope, read it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/3f7388f6f14ddddaa3bbeb88ac6c02cdbed1861eb638fdd33bff873f01af21ed.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "4081d122cab17447d2dcde2fa38f78ee74acaa59cbe3e866faa17c530842f4b1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "23cf308f58ee434760a62828b3938489436350003697998a07c251b4a6c81b89", "generation_seconds_batch": 20.045282036066055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1990060806274414, "target_z": 0.8281250641870852, "ce": 6.395919322967529, "genuineness": 4.65797233581543, "identity": 0.8178008794784546, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4081d122cab17447d2dcde2fa38f78ee74acaa59cbe3e866faa17c530842f4b1.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "40962b96b141ee2996529521a4202b36a59c9e5614e6627ea8e4dc5d2e7e0e65", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1b200b429ce9f9cb552a8fd48866a07ee59ab1250824f55221ab0eeb0bd4b42b", "generation_seconds_batch": 15.856095577008091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.056178092956543, "target_z": 0.6718749684158787, "ce": 6.046441555023193, "genuineness": 4.193545341491699, "identity": 0.6245622038841248, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/40962b96b141ee2996529521a4202b36a59c9e5614e6627ea8e4dc5d2e7e0e65.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "40a6e8d02fbdf6d9161f344dff9d56d2dbbafeb2a6aa29f5f24cb27c23235884", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "28e05e53eaba6c5bd2fed9ce632a963d971f5c65e074e04f439d700e7a9f68ab", "generation_seconds_batch": 21.121698254952207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2702152729034424, "target_z": 2.0, "ce": 5.689021587371826, "genuineness": 3.7416701316833496, "identity": 0.4385831356048584, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/40a6e8d02fbdf6d9161f344dff9d56d2dbbafeb2a6aa29f5f24cb27c23235884.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "413881fb5b69e5286ef4703b5d9374920a4c994070569054f460f508dd0aba63", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1fe9d6f90ae0c54cfcc3e5d0d77ec90d63b3179086469225fc5793f4c9422141", "generation_seconds_batch": 21.6509872530587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4560961723327637, "target_z": 1.1093749235868033, "ce": 6.109982967376709, "genuineness": 3.9173994064331055, "identity": 0.5527123212814331, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/413881fb5b69e5286ef4703b5d9374920a4c994070569054f460f508dd0aba63.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "41642b80eed9309982f5f9df569efa747f67702ffdd653f9cd2813a892203867", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dfce3a078d75ce412fc1fcaa48ca8a12971724ed4f718cda9276237e5cce6b34", "generation_seconds_batch": 19.66208574094344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3061270713806152, "target_z": 0.9453126360154901, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.6420338153839111, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/41642b80eed9309982f5f9df569efa747f67702ffdd653f9cd2813a892203867.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": "418b249a44023c567d94a7d050627483007ca334dd3e87cd6d31ff32aba0a72c", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Escribí el número en el sobre.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3eb4eb9ab1675be31f3ab76d3886d0074ad2877468fbaf0dce52572be15e345f", "generation_seconds_batch": 20.705657041980885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.891721248626709, "target_z": 1.5859374027005295, "ce": 6.1894097328186035, "genuineness": 4.3127899169921875, "identity": 0.6117845773696899, "hypothesis": "Escribí el número en el sobre, léelo bien, y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/418b249a44023c567d94a7d050627483007ca334dd3e87cd6d31ff32aba0a72c.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "41b0f5523d7ddfc32d0c0e7daef7c1f0c34c0a8818e6f8f4260edfcb6c343253", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "735cb52feefe2be92bd4156cb1ececf99f015c57732fa9391de9329f629594c9", "generation_seconds_batch": 20.843670643982477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.713186502456665, "target_z": 1.3906250438102328, "ce": 5.855817794799805, "genuineness": 4.18726921081543, "identity": 0.04862173646688461, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/41b0f5523d7ddfc32d0c0e7daef7c1f0c34c0a8818e6f8f4260edfcb6c343253.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "41c7ad7cd090b30746477b2377c887bf93cd743f2851f8d7cc8d497d528ee7a4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d8c358f08996c2ccb21f057b6f61ec009da3582240314184ccae71e77accf5a0", "generation_seconds_batch": 19.76421079202555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.527510166168213, "target_z": 1.1874999714724066, "ce": 6.221180438995361, "genuineness": 4.243753433227539, "identity": 0.2568008601665497, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/41c7ad7cd090b30746477b2377c887bf93cd743f2851f8d7cc8d497d528ee7a4.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "41ee83d54b1c2537a69925fae02bff02f7c45d273122c25e5de70a39062f1f93", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0a908627501356044a4d3b929f07977acf9522ca525767086da30c23f5c5eb2c", "generation_seconds_batch": 19.76421079202555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.598924160003662, "target_z": 1.2656250193580099, "ce": 6.252951145172119, "genuineness": 4.162164688110352, "identity": 0.15484930574893951, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/41ee83d54b1c2537a69925fae02bff02f7c45d273122c25e5de70a39062f1f93.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "422794d2ac7df90c07b7705c392141f09c4d0c5964ddeef36b3620c496bab9e0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a9cb9358e370bc3bcc337b63fe3d63e9a695ec65e7db488e73434fad136735d6", "generation_seconds_batch": 15.124819474993274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6274895668029785, "target_z": 1.2968748298532822, "ce": 6.252951145172119, "genuineness": 4.2751336097717285, "identity": 0.6754833459854126, "hypothesis": "ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/422794d2ac7df90c07b7705c392141f09c4d0c5964ddeef36b3620c496bab9e0.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "4277a01e2450fad86b46169894ce8f35fa9ed02bcb386a34de4db7d3177eefbe", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8357751d64adde322f5e6c20174097f6d4e99ce6855e0a4cd1377c5052b5a383", "generation_seconds_batch": 15.856095577008091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.070460796356201, "target_z": 0.6874998736635148, "ce": 6.284721851348877, "genuineness": 4.432034492492676, "identity": 0.7177426815032959, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4277a01e2450fad86b46169894ce8f35fa9ed02bcb386a34de4db7d3177eefbe.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "4294b7d888786528658f0a76e16cfcf57f975801a7c12b3726eaea5b82c28e11", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "422c3707041460a93f31731cdb5a27787f1144d18871fc11612c35b42294349f", "generation_seconds_batch": 23.362886833958328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.955993890762329, "target_z": 1.6562499979623146, "ce": 5.919358730316162, "genuineness": 4.118232727050781, "identity": 0.10942696034908295, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4294b7d888786528658f0a76e16cfcf57f975801a7c12b3726eaea5b82c28e11.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "42a337839a563f1a42c6d9022acc3ea6149aeb503bfc16503cca5519c168429e", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0b67b2e4ecba1e502c3c52f15602ee8922c14044762ffd5289f4d57b4f81361e", "generation_seconds_batch": 15.921878305030987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1490163803100586, "target_z": 0.7734376349966474, "ce": 6.41180419921875, "genuineness": 4.381826400756836, "identity": 0.6217833757400513, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/42a337839a563f1a42c6d9022acc3ea6149aeb503bfc16503cca5519c168429e.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "43419cee5d89039813f9db99a71d7e2ff8a51dd701f6502765833afc8544851d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2eba8a7b19142d62d5190a91204a7c875f5e389233600a016e71702c2958bdd", "generation_seconds_batch": 16.43171721091494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.077397584915161, "target_z": 1.7890624750383557, "ce": 6.0146708488464355, "genuineness": 3.9676074981689453, "identity": 0.07227133214473724, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/43419cee5d89039813f9db99a71d7e2ff8a51dd701f6502765833afc8544851d.mp3" }, { "id": "heldout-nl-2", "language": "nl", "sentences": [ "De weg gaat linksaf na de brug.", "Loop verder... tot aan het kleine houten hek.", "Ik wacht aan de andere kant." ], "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-2", "key": "434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Intense Interest. 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": "03c9fc15f26ccf888eb0e3394c96995fea385e0c6ebafa64fd44cdf4a37b404d", "generation_seconds_batch": 15.506036958075128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.252566337585449, "target_z": 0.8867185892775764, "ce": 6.197352409362793, "genuineness": 4.356721878051758, "identity": 0.7255650758743286, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder, tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.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": "437798139dd924edad2dfce5fb814afa7df2f6aca598549b342052fefd23e6df", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b347bcad5c70b49bc9fcf78d0850f270b8189a60a2a870d144112a79766c5304", "generation_seconds_batch": 20.63684871303849, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0847437381744385, "target_z": 0.7031250397348623, "ce": 6.141753673553467, "genuineness": 4.099404335021973, "identity": 0.30713921785354614, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/437798139dd924edad2dfce5fb814afa7df2f6aca598549b342052fefd23e6df.mp3" }, { "id": "heldout-es-3", "language": "es", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-3", "key": "43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Intense Interest. 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": "1f82ce4db82857bd4906197b82a75748d5100b38b1c18f736aca9917a75d0d96", "generation_seconds_batch": 15.754900276078843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.591782569885254, "target_z": 1.2578123059104804, "ce": 6.109982967376709, "genuineness": 4.494794845581055, "identity": 0.5845910310745239, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "4446db1cf9b4c2245d00778e7525236d26ac606e1c8eb7c0fcfc6f89adc79270", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "69f798a4fa4098280b2a27a098ecf3dfe2a5c64a6aa6625e6770a5e17aa41155", "generation_seconds_batch": 20.44154907995835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1454455852508545, "target_z": 0.7695312782728828, "ce": 6.046441555023193, "genuineness": 3.948779582977295, "identity": 0.18564781546592712, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4446db1cf9b4c2245d00778e7525236d26ac606e1c8eb7c0fcfc6f89adc79270.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "4451cbf9925424088fa5fb5787603dd607e12fac0f815d141d49d3088df785d6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1534729c08957ed57ddb7985c8276fac98916163f5e03e701239d6a9857315f", "generation_seconds_batch": 20.99159629002679, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.655850410461426, "target_z": 2.421874789099577, "ce": 5.796247482299805, "genuineness": 4.256305694580078, "identity": 0.4665643274784088, "hypothesis": "¡La puerta sigue abierta! ¡He dejado tu abrigo sobre la silla! Dime cuándo estás listo!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4451cbf9925424088fa5fb5787603dd607e12fac0f815d141d49d3088df785d6.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "44bdf6a37f737d70e856a0e5c8a7c93f782c8cbe5b5bad7b76da0f4214da18b3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7279c261d7f80436112ba192a6f54ab9ae95f18632633095272ed7f48c5c0b47", "generation_seconds_batch": 19.7807517379988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1702356338500977, "target_z": 1.8906248807954131, "ce": 6.109982967376709, "genuineness": 4.545003414154053, "identity": 0.43278029561042786, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/44bdf6a37f737d70e856a0e5c8a7c93f782c8cbe5b5bad7b76da0f4214da18b3.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "450264949714393787656192ac7d14bb982feb89882488cf1a0a7a46ce9edc00", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "84017de17f069b41153c76821028169673f60f792a68635113e6d02910709a10", "generation_seconds_batch": 22.335973759996705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.241854429244995, "target_z": 0.8750000407537049, "ce": 6.165581703186035, "genuineness": 4.444586753845215, "identity": 0.7319440841674805, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/450264949714393787656192ac7d14bb982feb89882488cf1a0a7a46ce9edc00.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "45d11d6daf843c8584689b1314e417a7f2b2acee666e71fac6748279ce82c05a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6c46bc8790aec5b841fbdc732c2b300a1246a4cfd2755ccebb6694d005775977", "generation_seconds_batch": 21.18491195095703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.498739719390869, "target_z": 2.2499997880807348, "ce": 6.125868320465088, "genuineness": 4.306513786315918, "identity": 0.5177674293518066, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/45d11d6daf843c8584689b1314e417a7f2b2acee666e71fac6748279ce82c05a.mp3" }, { "id": "heldout-de-4", "language": "de", "sentences": [ "Ich schrieb die Nummer auf den Umschlag.", "Lies sie genau... und prüfe die letzten beiden Ziffern.", "Ruf an, wenn du Zeit hast." ], "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-4", "key": "45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Intense Interest. 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": "d5acda7b2d358c0625088f7b0fd560aa1f7544ccbdcf94e1789e942655ff0362", "generation_seconds_batch": 15.53126096399501, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.248995780944824, "target_z": 0.882812493377523, "ce": 6.332377910614014, "genuineness": 4.256305694580078, "identity": 0.7155333757400513, "hypothesis": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "469a60f24c3525639babfaf94e4275bf1981653b4a8b98f7c14f899febde6c5f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1b8823afad6a6808c919559055ad178af077138c98f45bbb6e11213bfa4925f8", "generation_seconds_batch": 20.209325433941558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.106167793273926, "target_z": 0.7265623976063165, "ce": 6.070269584655762, "genuineness": 4.381826400756836, "identity": 0.27324503660202026, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/469a60f24c3525639babfaf94e4275bf1981653b4a8b98f7c14f899febde6c5f.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": "469bf38e0460e39563135acca2f1c53f3cc0e903a8e74c8e2270c071050a8dbf", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5de1b781e4d0aea185eb91537486a38c77f570ff3a976ad94ee0955407163508", "generation_seconds_batch": 15.538244222989306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.88457989692688, "target_z": 1.5781249500767116, "ce": 6.395919322967529, "genuineness": 4.256305694580078, "identity": 0.47149017453193665, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/469bf38e0460e39563135acca2f1c53f3cc0e903a8e74c8e2270c071050a8dbf.mp3" }, { "id": "heldout-fr-3", "language": "fr", "sentences": [ "Quelqu’un a déplacé la petite chaise bleue.", "Elle était ici... près de la grande bibliothèque.", "Nous la remettrons après le déjeuner." ], "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-3", "key": "47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Intense Interest. 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": "b6c8f400805a64629785347a1e81364066dbd27fbcc26708e47da8346a26a1db", "generation_seconds_batch": 17.244187982054427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.541792869567871, "target_z": 1.2031248767200426, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.6601908206939697, "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/emo_Interest/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "48274168108b691e08d5c79629df90bde0ef92c7e8bd4dfee6458b03ceda7f74", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e9f80840ab7c84006b57bc7f1186103233436dae32ff7e30df59e5c2a7a4f096", "generation_seconds_batch": 20.604531178018078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 6.252951145172119, "genuineness": 4.362998008728027, "identity": 0.6401186585426331, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/48274168108b691e08d5c79629df90bde0ef92c7e8bd4dfee6458b03ceda7f74.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "4832181b567ff4e8ec698d2ca479abf272cb507a39ffecb4a57e2dcefa950860", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "825d77b4cb2ee59dcfa99068e09b17a63d665569035913ad1e51c9415ab70329", "generation_seconds_batch": 15.691166584030725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3132684230804443, "target_z": 0.9531250886393081, "ce": 6.268836498260498, "genuineness": 4.036643981933594, "identity": 0.34746408462524414, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4832181b567ff4e8ec698d2ca479abf272cb507a39ffecb4a57e2dcefa950860.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "483230f5b0d956e9ee4cbae3ff910a5493b4f0ec5dce1611d0eb04f3ae532ac2", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "06f4d674add51ba910c88663ae04b9cc4070f97c9e77f1460e428241ee3e8baf", "generation_seconds_batch": 15.34972174395807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8702971935272217, "target_z": 1.5625000448290753, "ce": 6.181467056274414, "genuineness": 4.532451152801514, "identity": 0.541758120059967, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/483230f5b0d956e9ee4cbae3ff910a5493b4f0ec5dce1611d0eb04f3ae532ac2.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": "49cefa9172bd654fe8a9b0022ab9d9c349fb2e2b8c277566de6d85efba19f023", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "22f30371406268f7ca5267a7d130705ac0c8b778809e5aa8c3774ccc32a957bd", "generation_seconds_batch": 15.538244222989306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8702971935272217, "target_z": 1.5625000448290753, "ce": 6.38003396987915, "genuineness": 4.494794845581055, "identity": 0.47069767117500305, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/49cefa9172bd654fe8a9b0022ab9d9c349fb2e2b8c277566de6d85efba19f023.mp3" }, { "id": "heldout-es-0", "language": "es", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-0", "key": "49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Intense Interest. 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": "60c0ba3665007104272c07f1501c9b8c88450e3d2c741bdac74969df495cbe8d", "generation_seconds_batch": 15.413211503066123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4418134689331055, "target_z": 1.0937500183391673, "ce": 6.260893821716309, "genuineness": 4.406930446624756, "identity": 0.6557091474533081, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "4a3ded2d84c1badaa620ffc985f1c6d283feb1f8b84dd53a4413ec60495cbac2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "864cf4525e8e4bd7be2b4c13c6507675685028c5636632c0e67fe5c86101d48e", "generation_seconds_batch": 20.257816315977834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2561371326446533, "target_z": 0.890624946001341, "ce": 6.3641486167907715, "genuineness": 4.632867813110352, "identity": 0.4585190415382385, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4a3ded2d84c1badaa620ffc985f1c6d283feb1f8b84dd53a4413ec60495cbac2.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "4a5d638fd60b6ac642779b3ea6c63ddd2701d2e24e21a1795d1f47f3367d074c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ef33969b70fc73e5b4fb5e21613ab0582f3ac7cf954a9880dbc4ac375b052d7b", "generation_seconds_batch": 19.839591957977973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.763176202774048, "target_z": 1.4453124730006706, "ce": 6.046441555023193, "genuineness": 4.005263805389404, "identity": 0.23469717800617218, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4a5d638fd60b6ac642779b3ea6c63ddd2701d2e24e21a1795d1f47f3367d074c.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "4a6434ad60d346ae7db25bf40c7be1a49ff0c39c8971427b504f399a5f95a658", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "034f2b3344676872baadc1f55933a94a60bbde24b1bf0fa957df50e0b09a3dad", "generation_seconds_batch": 21.571684465976432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6846208572387695, "target_z": 1.3593749724912492, "ce": 6.165581703186035, "genuineness": 4.017816066741943, "identity": 0.09035884588956833, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4a6434ad60d346ae7db25bf40c7be1a49ff0c39c8971427b504f399a5f95a658.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": "4bbf16c0ac4e00d553fc0c4af92182cecc751781bb725b2753a2219d6b19a32d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d6d47149fded1d0736ba7ca5a95bc663a3d3d2c1000faf8918f9fd2876d91ad0", "generation_seconds_batch": 16.977099837036803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.784600257873535, "target_z": 1.4687498308721247, "ce": 6.054384231567383, "genuineness": 4.20609712600708, "identity": 0.38507574796676636, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4bbf16c0ac4e00d553fc0c4af92182cecc751781bb725b2753a2219d6b19a32d.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": "4becb589aa74fc37920ce8f73177c4ce388e2d508983baecbdc1c6367b965412", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "63c84140e6b7719fa43ff01dff3da22c2e860b4569df9bf708d213b14add3a5d", "generation_seconds_batch": 20.976191518944688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3239803314208984, "target_z": 0.9648436371631796, "ce": 6.348263263702393, "genuineness": 4.557555198669434, "identity": 0.4782702922821045, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zum kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4becb589aa74fc37920ce8f73177c4ce388e2d508983baecbdc1c6367b965412.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "4bf34ff475456f3801571c414bfd361dea9e572c2f52ec5ee1af87499e799252", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9fc33dd91fc3597fff3280cb3c6c2cbf2479e3fa2030683e208133035f2f6287", "generation_seconds_batch": 19.896188564947806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4560961723327637, "target_z": 1.1093749235868033, "ce": 6.022613525390625, "genuineness": 3.7667744159698486, "identity": 0.620306670665741, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4bf34ff475456f3801571c414bfd361dea9e572c2f52ec5ee1af87499e799252.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "4c59cb06e122774bc7782598b9e13b609d9f0364b3923eb38b726bf489699bcf", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f87d83e40ec7b80ae3b6c9f9deb8c9b73888d646c640cdc3276ed07b23ee9234", "generation_seconds_batch": 19.999672765959986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7417521476745605, "target_z": 1.4218751151292164, "ce": 6.09409761428833, "genuineness": 3.7918784618377686, "identity": 0.4574154019355774, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4c59cb06e122774bc7782598b9e13b609d9f0364b3923eb38b726bf489699bcf.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": "4cf97d4670a0450d2e6ad66ae0c8726d45c480d14a86b608816c1c08e8b2253c", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1639ede74725cca075a2b21c9d7507ccb8fa0b8a04adacd578f48b73fe605c38", "generation_seconds_batch": 16.933233952964656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.906003952026367, "target_z": 1.6015623079481658, "ce": 6.348263263702393, "genuineness": 4.319066047668457, "identity": 0.40193691849708557, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4cf97d4670a0450d2e6ad66ae0c8726d45c480d14a86b608816c1c08e8b2253c.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": "4d152ccb63193424e15eda4ccdb5ec2df2b301a13e0bfc2e002aff4503bd5597", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1da142e7f3bc89f2c9acf608ac4135d9b2d3c88df18825f46cbb3c684f437bc3", "generation_seconds_batch": 20.678066977998242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7274692058563232, "target_z": 1.4062499490578688, "ce": 6.221180438995361, "genuineness": 4.406930446624756, "identity": 0.627061128616333, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4d152ccb63193424e15eda4ccdb5ec2df2b301a13e0bfc2e002aff4503bd5597.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "4d4c27893e5fab7602ca4a46fd6e428651d1b07abe5eb7c503c446956aae7d89", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fc06e370104e02e61b4a7c3d4fb79f847b7e495abdb89ca14bcd86a0c0598364", "generation_seconds_batch": 21.204900555079803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.406106472015381, "target_z": 1.0546874943963656, "ce": 6.197352409362793, "genuineness": 4.306513786315918, "identity": 0.44016844034194946, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4d4c27893e5fab7602ca4a46fd6e428651d1b07abe5eb7c503c446956aae7d89.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "4d571953a8a78e37039129ad8e009da39dbb0782cf9d878f7d5ad165f0deb969", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b4c9ad7c650ab7cd4911772e388b28822d2b491c254e4e9e121e8f24001a5d70", "generation_seconds_batch": 20.820797253982164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5132274627685547, "target_z": 1.1718750662247703, "ce": 6.022613525390625, "genuineness": 4.281409740447998, "identity": 0.2602909803390503, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4d571953a8a78e37039129ad8e009da39dbb0782cf9d878f7d5ad165f0deb969.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "4d74d747c8b10bb01b7da1d94344156b0e426c7b7cb084feb5ed722865027f13", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e8914841d7f01a93b7646a832f68e42397dab760760b2b5128dca7e4105a7698", "generation_seconds_batch": 23.09919051604811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.055973529815674, "target_z": 1.7656251171669015, "ce": 6.086154937744141, "genuineness": 4.262581825256348, "identity": 0.2672737240791321, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4d74d747c8b10bb01b7da1d94344156b0e426c7b7cb084feb5ed722865027f13.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "4daa2047be89dc4675382c524151b21752ea1658655f5c8ef981c5412e003369", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d8507a3212be350fd04dcca3c35a9c375ecbfaaa8df6036e027ecb73efa7f027", "generation_seconds_batch": 21.006562340073287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.35591197013855, "target_z": 2.0937499531332393, "ce": 5.589737892150879, "genuineness": 3.911123275756836, "identity": 0.3755611777305603, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4daa2047be89dc4675382c524151b21752ea1658655f5c8ef981c5412e003369.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "4ec62ab0e096e389a1ed21744d0b1b9e8d6976453bc3a1389714ea6d594b49f7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "213e6f12e4e13801a25869fffa13752a304452cd3d70e94338286dbc84b3a982", "generation_seconds_batch": 21.50847610097844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4489548206329346, "target_z": 1.1015624709629852, "ce": 6.0305562019348145, "genuineness": 3.860914945602417, "identity": 0.36717769503593445, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4ec62ab0e096e389a1ed21744d0b1b9e8d6976453bc3a1389714ea6d594b49f7.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "4f46ff7c6c2c4b1d8bdba1bcf91e1bac3c67422264ca69c3bec9fbbd8cb5bdd4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "447b1a5d0ad16b1949c985662a031cb9e7e88cdd25c73a8081f9ccf461e5f15f", "generation_seconds_batch": 14.813869612989947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3989651203155518, "target_z": 1.0468750417725474, "ce": 6.165581703186035, "genuineness": 4.137060642242432, "identity": 0.29300153255462646, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4f46ff7c6c2c4b1d8bdba1bcf91e1bac3c67422264ca69c3bec9fbbd8cb5bdd4.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "4f64b0c92b728e8d77cfeb7ef51a02cbef755bf580e40775d5e5793647b44a67", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ecc438bd3514dababdd1df91682c13ea302f9861ce54d92bddb258af3bf4f39d", "generation_seconds_batch": 20.410871675005183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5132274627685547, "target_z": 1.1718750662247703, "ce": 6.133810997009277, "genuineness": 3.835810661315918, "identity": 0.36226052045822144, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4f64b0c92b728e8d77cfeb7ef51a02cbef755bf580e40775d5e5793647b44a67.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "4f65dc889b6ead37d69243a90fc496ce71771ca86ad09e828791a55587291132", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9cdb43cc7f10613181c6ad9056c0f50a42f6b57aed36ae6763f90e5e3b657731", "generation_seconds_batch": 23.641709966002963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5632171630859375, "target_z": 1.2265624954152081, "ce": 6.23706579208374, "genuineness": 4.406930446624756, "identity": 0.5476446151733398, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4f65dc889b6ead37d69243a90fc496ce71771ca86ad09e828791a55587291132.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "4f72609f9c6a6ebf74f14547ad188f93fcb701ab5998dfdfc3d5631008703ff1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "658b506d46b008ada4cc21360626b061763ef4a1149043d2a9a24ef283eec169", "generation_seconds_batch": 21.674231372075155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5560758113861084, "target_z": 1.2187500427913902, "ce": 6.173524379730225, "genuineness": 4.174716949462891, "identity": 0.4457979202270508, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4f72609f9c6a6ebf74f14547ad188f93fcb701ab5998dfdfc3d5631008703ff1.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": "4fb00ed9a9da5ba0fdcabdd40777a3c746fe43ad8daab9b09933838462a6417a", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89f2397fb3c19c77246fbc5d4532c9d024a192a9736a00a4dfa507ab995f823f", "generation_seconds_batch": 20.745220619020984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1059632301330566, "target_z": 1.8203125463573393, "ce": 6.221180438995361, "genuineness": 4.243753433227539, "identity": 0.6172382235527039, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4fb00ed9a9da5ba0fdcabdd40777a3c746fe43ad8daab9b09933838462a6417a.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "4fc32982ab53da619d9b52e8717f9578707ebc52e5c8d624e97c69a89327db7b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "42c8552e900f44f3ed4591411ee90f416773d8bc66150965d478043a22683439", "generation_seconds_batch": 14.96411123604048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2844982147216797, "target_z": 2.0156251660713473, "ce": 6.268836498260498, "genuineness": 4.507347106933594, "identity": 0.4669317901134491, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/4fc32982ab53da619d9b52e8717f9578707ebc52e5c8d624e97c69a89327db7b.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "502c80a7121667535ce1a39f25455a146f3d19bd6141d66bc87bd1c08e618fca", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dfec65c62a72fa09ca06488d06344b60468a407a6650a514217b8794b3fc697a", "generation_seconds_batch": 19.783948447089642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6132068634033203, "target_z": 1.281249924605646, "ce": 6.046441555023193, "genuineness": 4.344170093536377, "identity": 0.6531206369400024, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/502c80a7121667535ce1a39f25455a146f3d19bd6141d66bc87bd1c08e618fca.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "506709d9d091ca9cef2e751f0ccf6baecfb2ce2f98ebd70e18c50944f5e33e35", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "95876051b09c853ddd9272acb75aafa0076c11d06066eb8be70a6f8405c3598e", "generation_seconds_batch": 19.788862611050718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7274692058563232, "target_z": 1.4062499490578688, "ce": 6.348263263702393, "genuineness": 4.507347106933594, "identity": 0.37388932704925537, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/506709d9d091ca9cef2e751f0ccf6baecfb2ce2f98ebd70e18c50944f5e33e35.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "50a5c88d88af12b79a1038d632cd8aa0b2e07839c504d6ac3a23516324dc13fd", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4bb7d3046b426a7a9816725961ed7304ee0bdfdcb3de41990477f2eba441b67d", "generation_seconds_batch": 20.25487637508195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 6.284721851348877, "genuineness": 4.168440818786621, "identity": 0.5220561027526855, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/50a5c88d88af12b79a1038d632cd8aa0b2e07839c504d6ac3a23516324dc13fd.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": "50bb80d338e27046d347887745f5fbd2abf0e9ff81a23c364f06d791281e76dd", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a49b7ec75bfd416a95db36a3c4aa0e85583acffc156aa13387a9958f5f26ea02", "generation_seconds_batch": 15.576037400984205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3204097747802734, "target_z": 0.9609375412631262, "ce": 6.09409761428833, "genuineness": 4.124508857727051, "identity": 0.3637182116508484, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, liß sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/50bb80d338e27046d347887745f5fbd2abf0e9ff81a23c364f06d791281e76dd.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "5130912402fda662e08222554a7fe8cf1080ce10dbb830d0790bdd095e6e8be2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "669047f90bcd5702d5d20fa400d57c27881789105799e16774b5478de1619009", "generation_seconds_batch": 20.288220369024202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.106167793273926, "target_z": 0.7265623976063165, "ce": 6.173524379730225, "genuineness": 4.419482707977295, "identity": 0.7152396440505981, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5130912402fda662e08222554a7fe8cf1080ce10dbb830d0790bdd095e6e8be2.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "5139189f6d211df56b08789ac96a75a42f6b0d1748f629884e6fc27240078fa8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c29c22c0205eecfd7e8c9af603d9d3da7f20aacdabacf465398ed115db3c79f5", "generation_seconds_batch": 17.045546013046987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.541792869567871, "target_z": 1.2031248767200426, "ce": 6.1020402908325195, "genuineness": 4.231201171875, "identity": 0.5966532826423645, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5139189f6d211df56b08789ac96a75a42f6b0d1748f629884e6fc27240078fa8.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "51893c010a878129f968ebfae2e21d7734dc47db26cca8b2d76af72526642df7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1eac21d3f674c4b858b444fb5c516aee09ef748658cff0686f2b28f7846850cd", "generation_seconds_batch": 19.771799605921842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9774179458618164, "target_z": 1.679687355833769, "ce": 5.792276382446289, "genuineness": 3.7918784618377686, "identity": 0.33278441429138184, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/51893c010a878129f968ebfae2e21d7734dc47db26cca8b2d76af72526642df7.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "51b6651a41b131cb5fef3c086661465a25df40fc2bd3185cf01d0ae084267aa5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f56806777976eb0583223466f6bde540a2e7dd8a71c08aa3731ca747c6b86032", "generation_seconds_batch": 21.254621229949407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.906003952026367, "target_z": 1.6015623079481658, "ce": 6.348263263702393, "genuineness": 4.268857479095459, "identity": 0.4661126136779785, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/51b6651a41b131cb5fef3c086661465a25df40fc2bd3185cf01d0ae084267aa5.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": "51d90ab6eb4df4aed7e624671cc0e76646f2448a27bc899e8d8d255a0fc57bd5", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fcb318635b82ab924295d412bda7d3f907bc1d71028c3ff33c2018aba5302df", "generation_seconds_batch": 17.1899752629688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7488932609558105, "target_z": 1.429687306929323, "ce": 6.324435234069824, "genuineness": 3.8922953605651855, "identity": 0.5208348035812378, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/51d90ab6eb4df4aed7e624671cc0e76646f2448a27bc899e8d8d255a0fc57bd5.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "5215443576a7a585493ae77b4d77067269df276c450ffa0e4df9ab891da9218c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "44a19df5840df0ab255e94ceae4c76f5cb3eedfefab68254215d4e61488bb06e", "generation_seconds_batch": 21.2093383789761, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.406106472015381, "target_z": 1.0546874943963656, "ce": 6.1020402908325195, "genuineness": 4.287685871124268, "identity": 0.5953692197799683, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5215443576a7a585493ae77b4d77067269df276c450ffa0e4df9ab891da9218c.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "528e2c213828c334ca4d1b826b484a8a0e23611480895be22d46dfc951dfa27f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "90ceb8802d6e3e6bb0b3d0c8c380ddbe871ced5f9b96d00332faf0e383ec1969", "generation_seconds_batch": 15.317588392994367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9774179458618164, "target_z": 1.679687355833769, "ce": 6.046441555023193, "genuineness": 4.268857479095459, "identity": 0.5866457223892212, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/528e2c213828c334ca4d1b826b484a8a0e23611480895be22d46dfc951dfa27f.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": "52fa6c3b7c72c12f09e95f82cd9b6306539a7ebda7940828882f48c7e2f87f77", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The keys are on the kitchen table.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ba46edd5afaaeb66a0cef6bf925bd88167f73aa84f148f2323a07dbe2073c51", "generation_seconds_batch": 15.507243506028317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5489344596862793, "target_z": 1.210937590167572, "ce": 6.2767791748046875, "genuineness": 4.168440818786621, "identity": 0.5614129304885864, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/52fa6c3b7c72c12f09e95f82cd9b6306539a7ebda7940828882f48c7e2f87f77.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "531545c4cce095ccc2867f46e83c00a24c9eb649dca2fc85245e8aa92a4ef876", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f34cfce7fb56abefadc329fd12f629aed5f06d267eff1e97aa9634903aefaf4e", "generation_seconds_batch": 15.048330485005863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.34897518157959, "target_z": 0.9921873517583985, "ce": 6.165581703186035, "genuineness": 4.595211505889893, "identity": 0.5461745262145996, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/531545c4cce095ccc2867f46e83c00a24c9eb649dca2fc85245e8aa92a4ef876.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "533cd968782187b6f5733169a49aa3f5767c896cf31d499993d24bc3ee5908fc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dfab484809bc2fea1792059fe0e72b657ed45e420b60abd5b47103b81cd7825e", "generation_seconds_batch": 19.63052638003137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1490163803100586, "target_z": 0.7734376349966474, "ce": 6.062326908111572, "genuineness": 4.162164688110352, "identity": 0.16798120737075806, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/533cd968782187b6f5733169a49aa3f5767c896cf31d499993d24bc3ee5908fc.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "5355f6e953639f2cebc8617cddfd113a5a71747c30446f386e25a29c5d1b0c90", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "90dbb952286bc437c33fa4a5b179daa475748784bc8905694176b88497b0edf1", "generation_seconds_batch": 15.348714818013832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1383042335510254, "target_z": 0.7617188256490647, "ce": 6.1894097328186035, "genuineness": 4.20609712600708, "identity": 0.7495652437210083, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5355f6e953639f2cebc8617cddfd113a5a71747c30446f386e25a29c5d1b0c90.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "537326b366a7f07733a153428b87e24cf13a3a206228cc4e52abe9a413e55eee", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8fa2f42f852dc5620892a7451e442e6c2196185555cf4a7c185c6b11840cf4f8", "generation_seconds_batch": 20.760876609012485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3132684230804443, "target_z": 0.9531250886393081, "ce": 6.046441555023193, "genuineness": 4.381826400756836, "identity": 0.49109935760498047, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/537326b366a7f07733a153428b87e24cf13a3a206228cc4e52abe9a413e55eee.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "53959c7248f598cebed433e508687c90ca0ac7dea44e5e362810003e36c1544a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ba0849a49b1ce1dc73732d9463861355a48e362f30acce82596f9f231a24514f", "generation_seconds_batch": 21.987211835104972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.784395694732666, "target_z": 2.5624999796231474, "ce": 6.006728172302246, "genuineness": 4.143336772918701, "identity": 0.4469878673553467, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/53959c7248f598cebed433e508687c90ca0ac7dea44e5e362810003e36c1544a.mp3" }, { "id": "heldout-de-4", "language": "de", "sentences": [ "Ich schrieb die Nummer auf den Umschlag.", "Lies sie genau... und prüfe die letzten beiden Ziffern.", "Ruf an, wenn du Zeit hast." ], "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-4", "key": "546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Intense Interest. 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": "220cfc4d84a48783fb2c982b8bae9db383d4f44d11ab6989ed98885ca2b3f179", "generation_seconds_batch": 15.53126096399501, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9704813957214355, "target_z": 0.5781250152826394, "ce": 6.252951145172119, "genuineness": 4.011539936065674, "identity": 0.5297664403915405, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern, ruf an, wenn du Zeit hast.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.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": "552e95e44d40e1d899e8ecd47de5ed0d4cc0d5f000eb288f398e94adf01fb44d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The keys are on the kitchen table.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d9288cc30fa917888cf14febb68f4fa0c28c422e696a3993b8d4ff5727f9818f", "generation_seconds_batch": 15.348801995045505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9488525390625, "target_z": 1.6484375453384967, "ce": 6.109982967376709, "genuineness": 3.911123275756836, "identity": 0.31660139560699463, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/552e95e44d40e1d899e8ecd47de5ed0d4cc0d5f000eb288f398e94adf01fb44d.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "553d69be45b15d3507644a711c762d7a42bb47e069d2906b44b2773a1541bbb5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "189ffbced08e3d9e001899e9a9dcb9cdac3148cb78eab2efefc90ad52b1eeb6e", "generation_seconds_batch": 20.791929512983188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.284721851348877, "genuineness": 4.319066047668457, "identity": 0.6649013161659241, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/553d69be45b15d3507644a711c762d7a42bb47e069d2906b44b2773a1541bbb5.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "554649c1d517040fadd0e97e64d075752ef9f4d454829be7d5510222b277f7d3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "21e818eef6e7f1036f95f5f16b23428feb63abd6c8867bbd987846155abbf613", "generation_seconds_batch": 17.859765148954466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9274282455444336, "target_z": 1.6249999266433313, "ce": 6.054384231567383, "genuineness": 4.143336772918701, "identity": 0.7423899173736572, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/554649c1d517040fadd0e97e64d075752ef9f4d454829be7d5510222b277f7d3.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "55c17eed30bc1bed2d655e023ee277809f1a77f115a4353aa5c5e75b136b75de", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f8251e7da68446bf38938d47ff39c8a2e4f3bca69e2e3028691fd062c14e7ed0", "generation_seconds_batch": 20.14129800896626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3168389797210693, "target_z": 0.9570311845393615, "ce": 6.395919322967529, "genuineness": 4.18099308013916, "identity": 0.7356106042861938, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/55c17eed30bc1bed2d655e023ee277809f1a77f115a4353aa5c5e75b136b75de.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "55ddb08fb170e0160ab9c64434d9ea2315f64708a019dee14de385128153c8d5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "860be555b8b93a5ed54b25875b6085698bd6f235b54d853120f50f82398cf3e0", "generation_seconds_batch": 19.84002809296362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0274078845977783, "target_z": 1.734375045847918, "ce": 5.7684478759765625, "genuineness": 4.099404335021973, "identity": 0.6509853601455688, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/55ddb08fb170e0160ab9c64434d9ea2315f64708a019dee14de385128153c8d5.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "560e6fd8049a53b8ca6ddb8d514b69795d35c35583577ebe5d0d2ef227afba9c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c81bfd2cabc252034588aecac742cec5aae4ae891e79e28fbdd8cf90bbc128b4", "generation_seconds_batch": 22.554005510988645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6917624473571777, "target_z": 1.3671876859387786, "ce": 6.141753673553467, "genuineness": 4.20609712600708, "identity": 0.5598587989807129, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/560e6fd8049a53b8ca6ddb8d514b69795d35c35583577ebe5d0d2ef227afba9c.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "56477c739d0617e231e33cc85c91e87d8af33d4961e18b2e156cbb6315737e46", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "db76c24fcaeb6df4c7c5a0869e861d178c9a5807495061c35f6fb9f01f632cde", "generation_seconds_batch": 19.63052638003137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 6.157639026641846, "genuineness": 4.344170093536377, "identity": 0.4559473395347595, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/56477c739d0617e231e33cc85c91e87d8af33d4961e18b2e156cbb6315737e46.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": "565dfd94fabc12927e871424ffa737a6f8f1354f17f38a4d8b04dcd04ead7f12", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Escribí el número en el sobre.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14d0a02ee97fe6761d812d6dfbf363995afa01338c85a5783d4e2fb7181dd703", "generation_seconds_batch": 16.87606308294926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5703585147857666, "target_z": 1.2343749480390263, "ce": 6.24500846862793, "genuineness": 4.068024158477783, "identity": 0.6177693605422974, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/565dfd94fabc12927e871424ffa737a6f8f1354f17f38a4d8b04dcd04ead7f12.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "57038754f6f8ce7998b19bdc6641aa48f0eede8a6c036dc5b4cb0c898ed553d4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "81cc3f064495bfb07f134ea0c3d01e0bf193d897f07ef893ec32366cf46d781f", "generation_seconds_batch": 20.563740335055627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1131045818328857, "target_z": 1.8281249989811574, "ce": 6.284721851348877, "genuineness": 4.432034492492676, "identity": 0.5431427955627441, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/57038754f6f8ce7998b19bdc6641aa48f0eede8a6c036dc5b4cb0c898ed553d4.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "57bf1abcbcbff5d386a9a3feb53bdfc58867c1332c65f8254eea323ba072cc53", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "75ee283d8f6d47507fa1b4343fa5008c1483df1bafeeded2b38a63c443e1535f", "generation_seconds_batch": 16.088412580895238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.113309383392334, "target_z": 0.7343751110538458, "ce": 6.403861999511719, "genuineness": 4.256305694580078, "identity": 0.3841891288757324, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/57bf1abcbcbff5d386a9a3feb53bdfc58867c1332c65f8254eea323ba072cc53.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": "57e907fe94df852562cedc45d58764ca1cf370fedcb4f79c7a447311341ece98", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Someone moved the little blue chair.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cba54fba58ab43804960f1e47d8bb7db32aa7edd43833e67aace8d3a7644f47b", "generation_seconds_batch": 15.388404171098955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4918031692504883, "target_z": 1.1484374475296049, "ce": 6.459460258483887, "genuineness": 4.319066047668457, "identity": 0.43205538392066956, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/57e907fe94df852562cedc45d58764ca1cf370fedcb4f79c7a447311341ece98.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "57fc707ad112b14bac96058f53eba0434483efe8fbe8b046dbe2d89dfab9a821", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "94441dad20e8f8ae75a412ffe3c12f78fb2bb6e4054e033ba4f1501fb4b68cd0", "generation_seconds_batch": 21.96642640104983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2345082759857178, "target_z": 1.9609374760571985, "ce": 6.046441555023193, "genuineness": 4.20609712600708, "identity": 0.1798752099275589, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/57fc707ad112b14bac96058f53eba0434483efe8fbe8b046dbe2d89dfab9a821.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "581920ba184245761312addf6c49d6caa1416f40c3d9f0a7975724ace2708617", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "08f472e37ea294b2543225e3be8d98cc51f5dae3442aa36fcb5cd071e4490f91", "generation_seconds_batch": 20.766756149940193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.498739719390869, "target_z": 2.2499997880807348, "ce": 6.0305562019348145, "genuineness": 4.005263805389404, "identity": 0.517795741558075, "hypothesis": "I found the little box! It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/581920ba184245761312addf6c49d6caa1416f40c3d9f0a7975724ace2708617.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "58a2547bfeb6725187654655bd33f1366a66badc0fdb7d6a9c52a8231873a85e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a5393cf0589bf95b227e8560f83d347ecb54ed601a5c871caab660e2c72c84b2", "generation_seconds_batch": 19.638973752968013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.056178092956543, "target_z": 0.6718749684158787, "ce": 6.038498878479004, "genuineness": 4.444586753845215, "identity": 0.5409958362579346, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/58a2547bfeb6725187654655bd33f1366a66badc0fdb7d6a9c52a8231873a85e.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "58f68e40ff212c016336a0e3f91d327a321635919edab4bb84a642bd616ab746", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0951fbeb0dd2bd32f966dad6c9a0d837e98c5737bc975263b70ca1231eafdc7e", "generation_seconds_batch": 16.148321163025685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.484457015991211, "target_z": 2.2343748828330985, "ce": 6.09409761428833, "genuineness": 3.6663577556610107, "identity": 0.5802958607673645, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/58f68e40ff212c016336a0e3f91d327a321635919edab4bb84a642bd616ab746.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "5945965d3b83da5e1cd5f3d33a05f618ae8001a39124944389518e1b2dcefbf1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0dd65c895117564387d238c75cd61b2b0215ff42b946db445151c1068ff38fc0", "generation_seconds_batch": 20.478779423981905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1454455852508545, "target_z": 0.7695312782728828, "ce": 5.77639102935791, "genuineness": 3.923675537109375, "identity": 0.5253971815109253, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5945965d3b83da5e1cd5f3d33a05f618ae8001a39124944389518e1b2dcefbf1.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "59952c2fdcc72ea418da085227440b99c0eb498cb1eed9479853dcc5557cee4f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "427d42d2b6522af0e1db0e6e4dc4324186307d3a278efeec54ac5bd435d481b6", "generation_seconds_batch": 19.999672765959986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.891721248626709, "target_z": 1.5859374027005295, "ce": 6.022613525390625, "genuineness": 3.8044304847717285, "identity": 0.3419795632362366, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/59952c2fdcc72ea418da085227440b99c0eb498cb1eed9479853dcc5557cee4f.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "59961e3bec8b427a20694c1f63fff6f2a4f15c8aa1cf563cc686ce02a712c656", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "860fc4b0532d44f35f034cfdb2dd761343e2794f92182ec4bbbb16fbf1202567", "generation_seconds_batch": 20.39060562895611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 6.221180438995361, "genuineness": 4.394378662109375, "identity": 0.284270316362381, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/59961e3bec8b427a20694c1f63fff6f2a4f15c8aa1cf563cc686ce02a712c656.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "59c88f48c68447b7d4ba2d7d0c3f0c4c568f65535c764b4ab0774ade613a8ed0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3655fa78774f8e25a8b30f3a4afcc71b02a90536183f65fd91ba19d9a0609009", "generation_seconds_batch": 19.822595144971274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.352545976638794, "target_z": 0.9960937084821632, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.44432395696640015, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/59c88f48c68447b7d4ba2d7d0c3f0c4c568f65535c764b4ab0774ade613a8ed0.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "59d3bba5d896741d6710584649fb9d27a64ff57715320748ea52601d3c3c3f69", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "56abf2acebe089e278c75eeb690ab175d63b05d568b5c560a88251f40f06bf12", "generation_seconds_batch": 21.3932950750459, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8651458024978638, "target_z": 0.4628906218161168, "ce": 6.284721851348877, "genuineness": 4.111956596374512, "identity": 0.4255899488925934, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/59d3bba5d896741d6710584649fb9d27a64ff57715320748ea52601d3c3c3f69.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "5a042326801cc7b4fb0d1b69b7e6e2e03590ac8045efb8be8e5d6d34a79411e8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2047bf8489df3d0a616c959c3e6242dd34b36cabe008482d2b6bd377fafe3838", "generation_seconds_batch": 17.592402137001045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.713186502456665, "target_z": 1.3906250438102328, "ce": 6.078212261199951, "genuineness": 4.168440818786621, "identity": 0.2348308116197586, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5a042326801cc7b4fb0d1b69b7e6e2e03590ac8045efb8be8e5d6d34a79411e8.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "5a1f6867846d48e7c0a2db60704f4fb5b6eb8f803cc6d557ec0c02e1eca67303", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ae6f9da262a8ccc00d5f5983caca7f5d22908db319bbc283ea66278477bc6734", "generation_seconds_batch": 19.33415228605736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6272850036621094, "target_z": 2.390624978604305, "ce": 6.078212261199951, "genuineness": 4.093128204345703, "identity": 0.5007067322731018, "hypothesis": "I found the little books. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5a1f6867846d48e7c0a2db60704f4fb5b6eb8f803cc6d557ec0c02e1eca67303.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "5a36e3b699846b3fc69abf8fc9a639a6cab65ea4590724fff9d2a040b7312cf8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d6093a3afd270d8a139c8f82f0344b2206b487c4f3ddc42a92fc1777846f0378", "generation_seconds_batch": 25.02811310708057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.191864490509033, "target_z": 0.8203123507395559, "ce": 5.927301406860352, "genuineness": 4.017816066741943, "identity": 0.15821592509746552, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5a36e3b699846b3fc69abf8fc9a639a6cab65ea4590724fff9d2a040b7312cf8.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": "5a62ea8a7414dabad56155ec18e43024fcc68c43d2cd8a569c080fe917ba0cb9", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "74cd87b7038219113ce129a3c3ac55ee4b9db639dc28b6212152e67184649469", "generation_seconds_batch": 20.775634670979343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3416292667388916, "target_z": 2.078125047885603, "ce": 6.046441555023193, "genuineness": 4.143336772918701, "identity": 0.536505937576294, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5a62ea8a7414dabad56155ec18e43024fcc68c43d2cd8a569c080fe917ba0cb9.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "5a8b6c7de89d9036f1f02ed381790bbece96bb3e2f496535790d5e43b8f823d6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9f595463de54dc571cde6bfb9059c033794b19bc82907c48e122f3b81fe9a564", "generation_seconds_batch": 20.63430152204819, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 6.141753673553467, "genuineness": 4.570107460021973, "identity": 0.43141287565231323, "hypothesis": "Ah la porte 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/emo_Interest/5a8b6c7de89d9036f1f02ed381790bbece96bb3e2f496535790d5e43b8f823d6.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": "5aac7648ba3c1cb3f6990c62ccd515890773c25c193c7dd1fbf8fa0df2a26082", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Someone moved the little blue chair.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c3b936b068b7e827443f47ed3d61cfdcd0dcf5141b44176688c56eeaadbeb94f", "generation_seconds_batch": 15.29444948094897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.777459144592285, "target_z": 1.460937639072018, "ce": 6.3641486167907715, "genuineness": 4.13078498840332, "identity": 0.392362117767334, "hypothesis": "Someone moved the little blue chair. It used to stand here, beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5aac7648ba3c1cb3f6990c62ccd515890773c25c193c7dd1fbf8fa0df2a26082.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "5ab7bf03909e2a505f64214b3435229b1b3ec1be4a6d46c795484e3bc4a66951", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9bc183f8004aa14c0ded54a79a12a9ef46c9909b54c34b2666d00a5c9fc7c088", "generation_seconds_batch": 19.747626291005872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.891721248626709, "target_z": 1.5859374027005295, "ce": 6.165581703186035, "genuineness": 4.13078498840332, "identity": 0.3489711284637451, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5ab7bf03909e2a505f64214b3435229b1b3ec1be4a6d46c795484e3bc4a66951.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "5abda93d403c16895ca6cb6c4bb1208c28610186e06de9871798cb0867de90e4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dc4ee5adb96b1a1d664fbb7f1ed6879ce78a61325edee24551ddd26097e653ab", "generation_seconds_batch": 20.89555896189995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.720327854156494, "target_z": 1.398437496434051, "ce": 6.141753673553467, "genuineness": 4.049196243286133, "identity": 0.04887501895427704, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5abda93d403c16895ca6cb6c4bb1208c28610186e06de9871798cb0867de90e4.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "5aeafec49623fffb17db019046d34d396209f4ebee0ff92dd1c361b780f77809", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f3ba136395f208b73e499902c1e39fe8ee2b66bd1424bb60b835d284863a04e8", "generation_seconds_batch": 15.34972174395807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.770317554473877, "target_z": 1.4531249256244885, "ce": 6.062326908111572, "genuineness": 4.400654315948486, "identity": 0.6272596716880798, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5aeafec49623fffb17db019046d34d396209f4ebee0ff92dd1c361b780f77809.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "5b7cf763c6cef9d7c1e5ec05dd4e5c6b68f976345f959039a525c1004de72b84", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc5313a69f691731f52c0dbe2052671ad1bd481511c942b3e3e72adcf5fb676a", "generation_seconds_batch": 16.88421765109524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.741547107696533, "target_z": 2.5156247422328164, "ce": 5.788304805755615, "genuineness": 4.005263805389404, "identity": 0.42705944180488586, "hypothesis": "¡La puerta sigue abierta! ¡He dejado tu abrigo sobre la silla! Dime cuándo estás lista!", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5b7cf763c6cef9d7c1e5ec05dd4e5c6b68f976345f959039a525c1004de72b84.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "5b9484f6ec278d42ff88c09ff4538f715b714491b64be12edff74f7b041be72c", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1fef4f5692ede4b300322e36a8c6c42fae9aa2abaace32fed204d538e6f8dd3e", "generation_seconds_batch": 16.19399583397899, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2561371326446533, "target_z": 0.890624946001341, "ce": 6.348263263702393, "genuineness": 3.9801597595214844, "identity": 0.32842886447906494, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5b9484f6ec278d42ff88c09ff4538f715b714491b64be12edff74f7b041be72c.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "5ba871b112c9d17bcdc0b29b51391597850a6bb4887b593084058c360ddf50d5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5de22e362a80e8bb8fc523dceb29f657e1c4c96c4d4fa3a8b2e8ec59af23461c", "generation_seconds_batch": 15.124819474993274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.102597236633301, "target_z": 0.722656301706263, "ce": 6.300607204437256, "genuineness": 4.306513786315918, "identity": 0.6244857311248779, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5ba871b112c9d17bcdc0b29b51391597850a6bb4887b593084058c360ddf50d5.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": "5be2e4aabc7c6057c18d8744acdfd96aee56bc8c82b40c02d3149bea230b98e4", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5cd9f3f8229b09ab9738b2d3ebe07907c28f0404bcf7929ee143c86d197aa3f4", "generation_seconds_batch": 17.703538216999732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.827448844909668, "target_z": 1.5156250682624557, "ce": 6.324435234069824, "genuineness": 4.281409740447998, "identity": 0.6279727816581726, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade. Dann neben dem Fenster. Nimm sie mit, wenn du gehst!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5be2e4aabc7c6057c18d8744acdfd96aee56bc8c82b40c02d3149bea230b98e4.mp3" }, { "id": "heldout-fr-2", "language": "fr", "sentences": [ "La route tourne à gauche après le pont.", "Continue... jusqu’à la petite barrière en bois.", "Je t’attendrai de l’autre côté." ], "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-2", "key": "5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Intense Interest. 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": "a66237775d9f5e0e6d93a24aad5bada8d609cee748084b439ce2ecf123a05b83", "generation_seconds_batch": 16.694984839065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6723281145095825, "target_z": 0.25195309685447254, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.8408834934234619, "hypothesis": "La route tourne à gauche après le pont. Continue, jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "5e0deda0f84cdfc20daf365e60119a41ec57438a39f8aa87341bb98d578b1844", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "61eb927e91c9d07bf239a5fe60a2d5c8ecfc13ccaf462960ebda370cc95bb371", "generation_seconds_batch": 23.434664042084478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8560142517089844, "target_z": 1.546874878757728, "ce": 6.125868320465088, "genuineness": 4.250029563903809, "identity": 0.6602163314819336, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5e0deda0f84cdfc20daf365e60119a41ec57438a39f8aa87341bb98d578b1844.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "5e26d278a09a7806b8247dec4b82405eeff515d17653be14587bfab31dbae7c7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ddaffd97634ce15355d8ff29bac5388d6655f2d4aac652f17621a54b59adf0a0", "generation_seconds_batch": 22.543488178984262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.520368814468384, "target_z": 1.1796875188485885, "ce": 5.597680568695068, "genuineness": 4.017816066741943, "identity": 0.5531224012374878, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5e26d278a09a7806b8247dec4b82405eeff515d17653be14587bfab31dbae7c7.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "5e68195f9dd7849ae7e0967f13da59d17469669551f5755d715b9c7aab427461", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c86f50b057e7828a64c5dd4cfe07032ddb835dda92a08123fd9153bd91438b7f", "generation_seconds_batch": 20.31206647795625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.898862838745117, "target_z": 1.593750116148059, "ce": 5.593709468841553, "genuineness": 3.835810661315918, "identity": 0.4553256034851074, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5e68195f9dd7849ae7e0967f13da59d17469669551f5755d715b9c7aab427461.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "5f0c4d6507de0a1a9322eea92e468059c272592607fa3968cc7653f264c88518", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "59a27cb8d4a51c04bb49cf33728c287e4c1c34dffce1a2939e5378f3766e08dd", "generation_seconds_batch": 20.424458410940133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.841731548309326, "target_z": 1.5312499735100917, "ce": 6.086154937744141, "genuineness": 3.8295347690582275, "identity": 0.36176198720932007, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5f0c4d6507de0a1a9322eea92e468059c272592607fa3968cc7653f264c88518.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "5f44ff4aa322230833cdcea43886c42d2a91c0505ae70d0a425ea3d6751a4ab2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "37592dd5e6c0cd47f9ac21c9d27b1a639f7d389749ab34741e870423efaa0159", "generation_seconds_batch": 23.302493105991744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0454659461975098, "target_z": 0.660156159068296, "ce": 6.125868320465088, "genuineness": 4.231201171875, "identity": 0.67820143699646, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5f44ff4aa322230833cdcea43886c42d2a91c0505ae70d0a425ea3d6751a4ab2.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "5f76438ffdf7ae2a8b5782a52da22276f42a2fab2b9ae8b1c4c3420a51caf597", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ebb6bc84663a0eb3e65c56c643ac81f00f2b8367802b7ecfb0e30736b7583941", "generation_seconds_batch": 16.43171721091494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2059426307678223, "target_z": 1.9296874047382149, "ce": 5.903473377227783, "genuineness": 4.030367851257324, "identity": 0.04372362419962883, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5f76438ffdf7ae2a8b5782a52da22276f42a2fab2b9ae8b1c4c3420a51caf597.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "5faabacd229df510e6916a76ba9f6c3c138bd3bfb4143049e7c0cd3148c11dfc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "873cf978c3d8e5d88e5d9eec6cdbba1b4547b55f21f53a560c1f4fcdb1351d3d", "generation_seconds_batch": 20.243690975010395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9919055700302124, "target_z": 0.6015625035659492, "ce": 5.871703147888184, "genuineness": 4.093128204345703, "identity": 0.5371450185775757, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5faabacd229df510e6916a76ba9f6c3c138bd3bfb4143049e7c0cd3148c11dfc.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "5ffb9080ac10b97280cafb80d3bc98817f37e35c3542b739be4dfd024d7427e1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d5ed835dd28463864d540e298a46ad73abffc0ec8ccc0f604acf27431fbc64d7", "generation_seconds_batch": 23.078368208021857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.052607536315918, "target_z": 0.6679688725158253, "ce": 6.109982967376709, "genuineness": 3.973883628845215, "identity": 0.7031438946723938, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/5ffb9080ac10b97280cafb80d3bc98817f37e35c3542b739be4dfd024d7427e1.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": "60180365a20650d0c3b073b40b35e7ab75c686afeafac0467052d566c3005aee", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce7941e10849b2ad4229a3ab03e83dcefc6d2cf33e2d1fdcf7ef20cc8574430d", "generation_seconds_batch": 20.66980470204726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.34183406829834, "target_z": 0.9843751599582917, "ce": 6.221180438995361, "genuineness": 4.168440818786621, "identity": 0.6224018335342407, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/60180365a20650d0c3b073b40b35e7ab75c686afeafac0467052d566c3005aee.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "6086d4e8eee3ac23f289ad9040e58b856d3b05a7320aecee0efdffdde66a8a82", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "08ad8481f950daa5313c8d646ebed3271104208717f5336ee72d3a4a7798c26f", "generation_seconds_batch": 15.428328430978581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.224000930786133, "target_z": 0.8554687787823041, "ce": 6.308549880981445, "genuineness": 4.632867813110352, "identity": 0.49506786465644836, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6086d4e8eee3ac23f289ad9040e58b856d3b05a7320aecee0efdffdde66a8a82.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "60ab2bc136e091f872c45afa990ad3f75754ff93faebe0c9eedcc915c615e335", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5212357ceb70a30969ddc28e5039a5ffe787a6fe91d2a9e498bda983e8c40d22", "generation_seconds_batch": 15.332521051052026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.663196563720703, "target_z": 1.3359373537960837, "ce": 6.221180438995361, "genuineness": 4.017816066741943, "identity": 0.40712419152259827, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/60ab2bc136e091f872c45afa990ad3f75754ff93faebe0c9eedcc915c615e335.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "60f8bf98bfafaa40819b31807c61f93605142d79dd78185151feacbdea25ddb3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f70d180adaf70f459fbe03df44d436b561915089960fe539717a87ac892d4ae3", "generation_seconds_batch": 21.357137451996095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.663196563720703, "target_z": 1.3359373537960837, "ce": 6.0146708488464355, "genuineness": 4.042920112609863, "identity": 0.31024545431137085, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/60f8bf98bfafaa40819b31807c61f93605142d79dd78185151feacbdea25ddb3.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "61208572254eefb1d3e50d3c82ad95a3b0fbf0f7b96204f3f22b7dfb864cb7c2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7433a02964af289fa8f7e9ef11489667a98ba9a1bff0b725f9135575265ab56a", "generation_seconds_batch": 19.86970088700764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0988216400146484, "target_z": 1.8124998329098099, "ce": 6.348263263702393, "genuineness": 4.231201171875, "identity": 0.34128695726394653, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/61208572254eefb1d3e50d3c82ad95a3b0fbf0f7b96204f3f22b7dfb864cb7c2.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "61dcd51233966e49a3fafccf4fbc1e43db993dda2c6a7a43b88b61292a36b951", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5f98e210ec0c27de29c80b23a3e460d7ca0ab9dda628e9be4f9b3e10ef6000f2", "generation_seconds_batch": 20.013902019010857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.298985481262207, "target_z": 0.9374999225679607, "ce": 6.133810997009277, "genuineness": 4.15588903427124, "identity": 0.6408835053443909, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/61dcd51233966e49a3fafccf4fbc1e43db993dda2c6a7a43b88b61292a36b951.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "62051661bea6b7dc71dc5b5c0bb9bfe51ddc081715dcd9c97e2911e6a7b4544e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7cd82067d67d1d07b49b4d52370c2a2d760dbfaf337eb35a46c2d73b1f0540a4", "generation_seconds_batch": 21.076050044968724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3096976280212402, "target_z": 0.9492187319155434, "ce": 5.967014789581299, "genuineness": 4.055472373962402, "identity": 0.5498694181442261, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/62051661bea6b7dc71dc5b5c0bb9bfe51ddc081715dcd9c97e2911e6a7b4544e.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "622943eb116ddc82dc18fb4b2d9832a3438ef10de21aedf96a82ac07b79652b7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "31a049d71a569f770591f56f07b2495b4792b780ac6199ec554669c18b6242c2", "generation_seconds_batch": 19.78528204304166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.363258123397827, "target_z": 1.007812517829746, "ce": 6.221180438995361, "genuineness": 4.093128204345703, "identity": 0.26238229870796204, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/622943eb116ddc82dc18fb4b2d9832a3438ef10de21aedf96a82ac07b79652b7.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "631db76a060b08671ad2c85e3e1333aa5fb70bfabc164e584d3c5c45dd79d838", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1e3609862be40302688c1c186f90ab6fc3ffdfd3920f6c9fb8ee5178bba05868", "generation_seconds_batch": 20.133378922007978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.070256233215332, "target_z": 1.7812500224145378, "ce": 5.903473377227783, "genuineness": 3.798154592514038, "identity": 0.5747700333595276, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/631db76a060b08671ad2c85e3e1333aa5fb70bfabc164e584d3c5c45dd79d838.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "636f643e869dd4c22dd8a4f4cf14bee9d91522a3a1d92933bf33b14739368f9e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "88e21894896a4817683b876453014d6c774ca55f2c41b347566e08c501354100", "generation_seconds_batch": 24.755143972928636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.841731548309326, "target_z": 1.5312499735100917, "ce": 5.7406487464904785, "genuineness": 4.250029563903809, "identity": 0.5086394548416138, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/636f643e869dd4c22dd8a4f4cf14bee9d91522a3a1d92933bf33b14739368f9e.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "63d77726960c303c7034e0ae2dab1cfd9726bc6ea101a49977aa63060970cc70", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4d3613029bec3f62bbbd2a5320fbe9415a1fd7d087610942d68e24e3b2ea32e9", "generation_seconds_batch": 15.958877866039984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9488525390625, "target_z": 1.6484375453384967, "ce": 6.070269584655762, "genuineness": 3.898571252822876, "identity": 0.6570596694946289, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/63d77726960c303c7034e0ae2dab1cfd9726bc6ea101a49977aa63060970cc70.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "647df60a982e79c6c651ea8d6902e8468454013ab42930dc9cbdbc5c14e3afab", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ba0ee97d095c7281ca3aad2c04451f1f66834584439e10087ad3287ba4d6eaef", "generation_seconds_batch": 23.713490245048888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.291844129562378, "target_z": 0.9296874699441426, "ce": 5.7247633934021, "genuineness": 3.7040140628814697, "identity": 0.36046141386032104, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/647df60a982e79c6c651ea8d6902e8468454013ab42930dc9cbdbc5c14e3afab.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "648f7597164293a4d722804f5d3834641d8a67b367bb7dbb514f4ec62db07bbe", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "55f28288548ed0077a5b74eeaa4ef82548fdcc92ac9d0be3868df8e899b633f6", "generation_seconds_batch": 20.256252120947465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6846208572387695, "target_z": 1.3593749724912492, "ce": 6.078212261199951, "genuineness": 3.722842216491699, "identity": 0.42570897936820984, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/648f7597164293a4d722804f5d3834641d8a67b367bb7dbb514f4ec62db07bbe.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "64cc49fab8ca9a989bb7721b8c9440b091ab5eb0b91c31854a7b4ec961667c9a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a15b214881fc9a5f5d1b0b2c0144b75548a8c0c78e7fc14f721295164e13b17b", "generation_seconds_batch": 19.77644963003695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.198801279067993, "target_z": 1.9218749521143967, "ce": 5.839932441711426, "genuineness": 4.055472373962402, "identity": 0.27094757556915283, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/64cc49fab8ca9a989bb7721b8c9440b091ab5eb0b91c31854a7b4ec961667c9a.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "65227e1e0c4db12d4259e420d7527ebcc2afe6712871e3bab7cdd802653d2737", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "53ddf7bcde69f2d74c7151812a4ee3197d93d4901f306ba25df29fef583c2a48", "generation_seconds_batch": 19.92497742897831, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.598924160003662, "target_z": 1.2656250193580099, "ce": 5.959072113037109, "genuineness": 3.3870739936828613, "identity": 0.4590141773223877, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/65227e1e0c4db12d4259e420d7527ebcc2afe6712871e3bab7cdd802653d2737.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "6549b99475512b728d70c1950fa9bd5a302dc8b0495091a5ed437364e329d767", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5e190d37618659cc6de1bd34b4c987d39df71754ef67a1447c83e0ee3d2f58e6", "generation_seconds_batch": 19.828951330971904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.255932331085205, "target_z": 1.9843748339286527, "ce": 6.125868320465088, "genuineness": 4.15588903427124, "identity": 0.7087171077728271, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6549b99475512b728d70c1950fa9bd5a302dc8b0495091a5ed437364e329d767.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "654d4bf7537883b388a12a6981cec68056f6e708b4b9ab1c368a562275e8dfe1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dc93986ef6e4ed09c5287adaf3489652534cddccb9ed08f8648825637ff822be", "generation_seconds_batch": 23.45117224403657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0418953895568848, "target_z": 0.6562500631682425, "ce": 6.181467056274414, "genuineness": 4.469690799713135, "identity": 0.5531582236289978, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/654d4bf7537883b388a12a6981cec68056f6e708b4b9ab1c368a562275e8dfe1.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "65a188bc83b665cd6ed21f62576c231d61821c37289d73170d3bfab98679e4b1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2609f797374725f5012c82e5ddb5320934d942eb30d9d024eff3deca702d5496", "generation_seconds_batch": 15.219877628958784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.527510166168213, "target_z": 1.1874999714724066, "ce": 6.229123115539551, "genuineness": 4.149612903594971, "identity": 0.4743773639202118, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/65a188bc83b665cd6ed21f62576c231d61821c37289d73170d3bfab98679e4b1.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "65a29e7134570693d9d89590c0d96c60dcbcb8020301413d8f0eed8760a253d0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "300370aa3d2836884b5bef456f6fc555a129309012db9ff083daaecf09ea5038", "generation_seconds_batch": 21.801082237041555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2561371326446533, "target_z": 0.890624946001341, "ce": 6.213237762451172, "genuineness": 3.998987913131714, "identity": 0.35484957695007324, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/65a29e7134570693d9d89590c0d96c60dcbcb8020301413d8f0eed8760a253d0.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "65b93ff9ff22cd70f481c688b067d513e6a45d0428fa5062abca2355805636cd", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3078fd6a58f2a8d7d9d98e59e5f2cbde384a7085f37aec518a25826a678a8b15", "generation_seconds_batch": 20.045282036066055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9490572214126587, "target_z": 0.5546875269993294, "ce": 5.784333229064941, "genuineness": 4.457139015197754, "identity": 0.8611530065536499, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/65b93ff9ff22cd70f481c688b067d513e6a45d0428fa5062abca2355805636cd.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "65c168dd2430af891d3461fbaa917939ff479fc5e3a9ddbc800b4dc4c9fc60d5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "80c2e8ab1c425b2a4ae2cd3441d77773d2ffce36649e51037fdfb59a9434b559", "generation_seconds_batch": 21.757493808981963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 5.7684478759765625, "genuineness": 3.6349775791168213, "identity": 0.42186427116394043, "hypothesis": "The door is still open! I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/65c168dd2430af891d3461fbaa917939ff479fc5e3a9ddbc800b4dc4c9fc60d5.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "667d087b53d3156a45afd831ac00f38483050258c3a1e3a3abf34a3ed198c517", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a8b217a55183434f73e180d2ebb6a19809195b83c1ff96619a56e8262e49385f", "generation_seconds_batch": 19.788862611050718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0845389366149902, "target_z": 1.7968749276621738, "ce": 6.173524379730225, "genuineness": 4.344170093536377, "identity": 0.5912672877311707, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/667d087b53d3156a45afd831ac00f38483050258c3a1e3a3abf34a3ed198c517.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "668cf652e3d99ee96f53e343693358f6b2af0db0d2a5f08262ecbc47762d865e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "265dcf0f0fac07e2d7e6f74210f5954ddb55a409ab5f1b12d5caca812b55525c", "generation_seconds_batch": 19.713481564074755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2704200744628906, "target_z": 0.9062501120726885, "ce": 6.562715530395508, "genuineness": 4.18099308013916, "identity": 0.7129192352294922, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/668cf652e3d99ee96f53e343693358f6b2af0db0d2a5f08262ecbc47762d865e.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "66b3866bc685d69590c2bba43610fe3410481d70bba865d6a1f2c92964c438d8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bad3c0daa5cf0aa38635f92f97e2c4eb822a41f83e3f4bb44147c35006658c17", "generation_seconds_batch": 20.46024883899372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.005983829498291, "target_z": 1.7109376879764637, "ce": 5.998785495758057, "genuineness": 4.218649387359619, "identity": 0.2556125819683075, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/66b3866bc685d69590c2bba43610fe3410481d70bba865d6a1f2c92964c438d8.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "66cfbfcf70df2a4ca48b9acedd6d04458f271405074a9d7ed0fd2afadb7df947", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c3fd3f49fb51722cfa0842b9db0573c2eb9b130b579b19e008d1e7a319780bd0", "generation_seconds_batch": 20.257816315977834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4989447593688965, "target_z": 1.1562501609771343, "ce": 5.919358730316162, "genuineness": 4.105680465698242, "identity": 0.35342273116111755, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/66cfbfcf70df2a4ca48b9acedd6d04458f271405074a9d7ed0fd2afadb7df947.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "66daa952df5b7cb272d5fa3d8548d0d78683c3f3e978846e687d7bfd53ccde6f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "37846d1a36f8b93663df31c43eeaaeaecb799e181db9570148e2c2981a292212", "generation_seconds_batch": 19.30839309003204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.077397584915161, "target_z": 1.7890624750383557, "ce": 5.847874641418457, "genuineness": 3.735394239425659, "identity": 0.5165812969207764, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/66daa952df5b7cb272d5fa3d8548d0d78683c3f3e978846e687d7bfd53ccde6f.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "67a06111557661469fff633d035a50d207e3f4db2bed57854285355dd207bd10", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f4aa00837bfb836d82bd52910b8e9cca566984187c61725a384eccc3d464b69a", "generation_seconds_batch": 15.332236928050406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0954556465148926, "target_z": 0.7148435882587337, "ce": 5.696964263916016, "genuineness": 3.8922953605651855, "identity": 0.3818007707595825, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/67a06111557661469fff633d035a50d207e3f4db2bed57854285355dd207bd10.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "682fc7af2bd42c077f6297a57edbef633e7af8764ab85f303e874bf83a24d58a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8f0b04ccd50b117ce66e90c7ff2efb9931e1259137ff1d27166e33c93e33df26", "generation_seconds_batch": 20.89555896189995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9490572214126587, "target_z": 0.5546875269993294, "ce": 5.80021858215332, "genuineness": 3.8295347690582275, "identity": 0.22274626791477203, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/682fc7af2bd42c077f6297a57edbef633e7af8764ab85f303e874bf83a24d58a.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "6849333025f1cc1751656be1fa824ccb0f8ee144dad592565fcf1a37d84e918f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d81af09f3961912006cc1af3a485305dc34bd0c269ecccb70ea0f85964f81150", "generation_seconds_batch": 15.143071830039844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120450735092163, "target_z": 0.7421875636776639, "ce": 6.006728172302246, "genuineness": 3.9550557136535645, "identity": 0.40808653831481934, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6849333025f1cc1751656be1fa824ccb0f8ee144dad592565fcf1a37d84e918f.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "68a9a5ea63501867c29302df9c00e1a71366a039a8a403c61899112a074fce71", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3d7e16d4ea1200fc1915be3dda0f7aedc82e3879e4b93bb3e77335f525601336", "generation_seconds_batch": 22.47596691409126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6703381538391113, "target_z": 1.3437500672436131, "ce": 6.1894097328186035, "genuineness": 4.306513786315918, "identity": 0.3543854355812073, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/68a9a5ea63501867c29302df9c00e1a71366a039a8a403c61899112a074fce71.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "68bc9483ebde43f81486b4840251fe56d161821a055ce3384927de32170d4127", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "761c87229e3620c389c4d37fa1e75bf6c5a8e7dae45e99f53d7aee2e61563b3a", "generation_seconds_batch": 15.134578297031112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5703585147857666, "target_z": 1.2343749480390263, "ce": 6.260893821716309, "genuineness": 4.143336772918701, "identity": 0.15062215924263, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/68bc9483ebde43f81486b4840251fe56d161821a055ce3384927de32170d4127.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "690e671a35fb2fa0b12fdc604f1083a731607f48197bd343e0c678aa8960571f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9bead2a2bf9be5bbd1d06a0a1474702f48cb5c5e478634556aa4f8d9eee2188a", "generation_seconds_batch": 20.133414746029302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8580044507980347, "target_z": 0.4550781691922987, "ce": 5.863759994506836, "genuineness": 4.545003414154053, "identity": 0.5189178586006165, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/690e671a35fb2fa0b12fdc604f1083a731607f48197bd343e0c678aa8960571f.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "691192f978eab5f020eee5b20284f96bcf40baa2b7edd93f0213e69d795f4c4d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "45a82ddc3c1574fbf227834b75d79563b01a9d9c8d143fe9d55fcef9b04b0e8f", "generation_seconds_batch": 24.022898443043232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7988831996917725, "target_z": 1.484374996943472, "ce": 6.205295085906982, "genuineness": 4.250029563903809, "identity": 0.6825801730155945, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/691192f978eab5f020eee5b20284f96bcf40baa2b7edd93f0213e69d795f4c4d.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "69a59a57ce32d396a66f76183f6c1f8e8e3f9bd4b221e771f2fec812ebbdfd79", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b25a1c24cf849cd6eb0f9196a05733dc134e5b0493e29f6766b814a29dce569c", "generation_seconds_batch": 15.084900197922252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2632784843444824, "target_z": 0.8984373986251591, "ce": 6.0146708488464355, "genuineness": 4.557555198669434, "identity": 0.5824733972549438, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/69a59a57ce32d396a66f76183f6c1f8e8e3f9bd4b221e771f2fec812ebbdfd79.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "69e74712068a77947433bae2d0dc02512d135e03bbd6b429ff9b5715df9e0dfc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa13dc0b4dca5b73c0321dadd55477c19ad6573b7067bde6d548952875d0a393", "generation_seconds_batch": 23.195569848059677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0916805267333984, "target_z": 1.8046876411097033, "ce": 5.927301406860352, "genuineness": 4.256305694580078, "identity": 0.5258334875106812, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/69e74712068a77947433bae2d0dc02512d135e03bbd6b429ff9b5715df9e0dfc.mp3" }, { "id": "heldout-en-4", "language": "en", "sentences": [ "I wrote the number on the envelope.", "Read it carefully... and check the last two digits.", "Call me when you have a moment." ], "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-4", "key": "6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb53ac4839e20760c9287ca79e4bd3863092c6e97cf54d240cae58e77598a40a", "generation_seconds_batch": 17.165115645038895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9633400440216064, "target_z": 0.5703125626588212, "ce": 6.395919322967529, "genuineness": 3.9550557136535645, "identity": 0.23412245512008667, "hypothesis": "I wrote the number on the envelope. Read it carefully. And check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "6b6147b83949b7edabb02022717eccbdcd2c259156ed5549a98874b18d438b2c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f505490e80279b9c2ddb912da0311ae815d2984f366841664d451a78d5135f86", "generation_seconds_batch": 15.052714107907377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.356116771697998, "target_z": 1.0000000652059278, "ce": 6.173524379730225, "genuineness": 3.760498285293579, "identity": 0.38525187969207764, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6b6147b83949b7edabb02022717eccbdcd2c259156ed5549a98874b18d438b2c.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": "6b84d14fb4961ade68057dcf025df56ac80534057dab0b8f50a6ac93f555afd7", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "314e25fdb18d643fa99ece0e272740d049d1cd24f12751a8e67aaa8b2bb0ec71", "generation_seconds_batch": 15.465024960925803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.370194911956787, "target_z": 2.1093751192045866, "ce": 6.213237762451172, "genuineness": 4.595211505889893, "identity": 0.7920357584953308, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6b84d14fb4961ade68057dcf025df56ac80534057dab0b8f50a6ac93f555afd7.mp3" }, { "id": "heldout-es-3", "language": "es", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-3", "key": "6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bdafc0009698960a840986adfc768cc8a480ea6b2b9a6808f90a4b6eaa6d4f9c", "generation_seconds_batch": 15.754900276078843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.706045150756836, "target_z": 1.3828125911864146, "ce": 6.348263263702393, "genuineness": 4.632867813110352, "identity": 0.5395169258117676, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "6bab9d7f227fc456bbe8ec942e1a21b280121e561b655d9f2bc49e0a4d8bfa71", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "96929d700bdf3a23b6d21d7762a5a79841a620ee9fa612db5e9a52cb786b18f6", "generation_seconds_batch": 22.335973759996705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3204097747802734, "target_z": 0.9609375412631262, "ce": 6.205295085906982, "genuineness": 4.394378662109375, "identity": 0.5493795275688171, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6bab9d7f227fc456bbe8ec942e1a21b280121e561b655d9f2bc49e0a4d8bfa71.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "6bb732fdd49ccfc3fe658f98cfa9cfbee3de8ba37e804f952211310faff4ddf0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e6642cb0bcfb3148c47e5ba1aa5e7b97084aef59547cf396e424d264b299e6bf", "generation_seconds_batch": 16.62863296701107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2630739212036133, "target_z": 1.9921875473761819, "ce": 5.95112943649292, "genuineness": 4.243753433227539, "identity": 0.41431906819343567, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6bb732fdd49ccfc3fe658f98cfa9cfbee3de8ba37e804f952211310faff4ddf0.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "6bc3624693e0783fabd82b10fee936f3e3ae38660d43051994ea0ebc4b130289", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4430cc4a25e2545a18f7f9f733c4b310f6a668a78a6c397cd7756da14f89b7f8", "generation_seconds_batch": 15.792541157919914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6846208572387695, "target_z": 1.3593749724912492, "ce": 5.982900142669678, "genuineness": 4.18099308013916, "identity": 0.115017369389534, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6bc3624693e0783fabd82b10fee936f3e3ae38660d43051994ea0ebc4b130289.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "6bfb8b90bac2720d73ec3f730e68c46d1a688fa172c9a045694e11749f5698a6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7e7c843847c172db6fdcce1bd5223d7f232ba20cf056ac8312f8394e6a39d1a5", "generation_seconds_batch": 19.828951330971904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.184518575668335, "target_z": 1.9062500468667607, "ce": 6.054384231567383, "genuineness": 4.381826400756836, "identity": 0.510635495185852, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6bfb8b90bac2720d73ec3f730e68c46d1a688fa172c9a045694e11749f5698a6.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "6c8a567c6c972a5f325146a2755649c9e181f144b6406322b6f46f54f62f0835", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0b147842c8c8a646e49998ab27c15cbf310958766be1719d7638493e4f9b0b67", "generation_seconds_batch": 20.46024883899372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7488932609558105, "target_z": 1.429687306929323, "ce": 6.09409761428833, "genuineness": 4.256305694580078, "identity": 0.6680985689163208, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6c8a567c6c972a5f325146a2755649c9e181f144b6406322b6f46f54f62f0835.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "6caa08b831808576adc4171f3bbc1891f50cf4ed2e1734aff292ee98aa9ea250", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9fa3c1c89e1157ad4394d5929f5f89058d3a2e9c6c46b6441ad9ad005ccefef5", "generation_seconds_batch": 20.670913356007077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8203072547912598, "target_z": 1.5078123548149263, "ce": 6.24500846862793, "genuineness": 4.356721878051758, "identity": 0.6615558862686157, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6caa08b831808576adc4171f3bbc1891f50cf4ed2e1734aff292ee98aa9ea250.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "6d21abf54b0da02fba717a52ace7545d67c2ee11ad66cf16133324f60b00bfd8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "04cf599a959774ec73aa680ded9bfee49d232e2009731231dd9a7669f47beae0", "generation_seconds_batch": 22.20256691100076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.191659927368164, "target_z": 1.9140624994905786, "ce": 6.173524379730225, "genuineness": 4.406930446624756, "identity": 0.37634629011154175, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6d21abf54b0da02fba717a52ace7545d67c2ee11ad66cf16133324f60b00bfd8.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "6dc6ab108b92fd39fbc4125f68bf109d6d5af11ea9c30f3717482a2763fc387f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1e050bcd099fd78542380a14ca2689b8a0f57ada997094f784b46a4bd9da5948", "generation_seconds_batch": 20.955746807041578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.470378875732422, "target_z": 1.1249998288344394, "ce": 6.173524379730225, "genuineness": 4.306513786315918, "identity": 0.4306352436542511, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6dc6ab108b92fd39fbc4125f68bf109d6d5af11ea9c30f3717482a2763fc387f.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "6e49315bccc841bd2b49a6729d31c29118cb7eb76086e4666c04745ed5b9b2e8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8c0bcfad1f48f92f5395c9202a7de8eb524001785bb9ac9297cbf47abbfdade0", "generation_seconds_batch": 20.126743236905895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.463237762451172, "target_z": 1.1171876370343328, "ce": 6.133810997009277, "genuineness": 4.268857479095459, "identity": 0.7258247137069702, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6e49315bccc841bd2b49a6729d31c29118cb7eb76086e4666c04745ed5b9b2e8.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "6e62ce5db4fecc47c545ac45fc106469597d1ab75fef19a6c1b2689cbc46827b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b4bad92e2d968bba917072f01686756870e7ae9520756899523eaacab8e3593f", "generation_seconds_batch": 24.46550685900729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9702768325805664, "target_z": 1.6718751640336622, "ce": 6.205295085906982, "genuineness": 3.8420867919921875, "identity": 0.4433121681213379, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6e62ce5db4fecc47c545ac45fc106469597d1ab75fef19a6c1b2689cbc46827b.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": "6e8b96e5fddd1cf45b45aca5e49313feeff1b67bf6a5b384cbc3d1085998d554", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a205349f59b1bf9bb58161247af09d21b3f84e8c01ad33d65f4f66eb2717a224", "generation_seconds_batch": 20.734128348063678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7274692058563232, "target_z": 1.4062499490578688, "ce": 6.316492557525635, "genuineness": 4.017816066741943, "identity": 0.701789379119873, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6e8b96e5fddd1cf45b45aca5e49313feeff1b67bf6a5b384cbc3d1085998d554.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "6ed0fb440a1d773a31541a0a59c7509925c86d4eef8ead23c9f3c642983055f0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2a79cb8a4be422d816b74d9476dd262157fcad8847d3595f556b18ffca32fa7a", "generation_seconds_batch": 26.57848693896085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9776227474212646, "target_z": 0.5859374679064574, "ce": 6.2767791748046875, "genuineness": 4.607763767242432, "identity": 0.6267075538635254, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6ed0fb440a1d773a31541a0a59c7509925c86d4eef8ead23c9f3c642983055f0.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "6edd9d0f43438fa9e4e2d84bdcb190e522ba930f9e72dbdaa49dd74a809b00f0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1c783c988f58db1bbddad22a32a0753a780fb5dec4cf91c41cd05f23565857a", "generation_seconds_batch": 20.165152195026167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7346105575561523, "target_z": 1.414062401681687, "ce": 6.205295085906982, "genuineness": 4.482243061065674, "identity": 0.5182864665985107, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6edd9d0f43438fa9e4e2d84bdcb190e522ba930f9e72dbdaa49dd74a809b00f0.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "6f5da30447843a7091af6df9f2abbc71cef2b3ac5741a7ec2bd9093d8679a04d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b8dea8bd214567398fe16b01922d2e9810066664e403ff70cddff01b10e9925f", "generation_seconds_batch": 15.7738140639849, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.298780918121338, "target_z": 2.0312500713189836, "ce": 6.229123115539551, "genuineness": 4.080576419830322, "identity": 0.6262168884277344, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6f5da30447843a7091af6df9f2abbc71cef2b3ac5741a7ec2bd9093d8679a04d.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "6f854997d8d106f089ed82af86794ddd48a1326fa3e6ef69b74bc068eb7856d3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a483b3a3ee19312c76a8a3e46cddf109dfc71b2d303ed09cddbf4d58ad32dace", "generation_seconds_batch": 15.21351994399447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3382632732391357, "target_z": 0.980468803234527, "ce": 6.205295085906982, "genuineness": 4.231201171875, "identity": 0.4411940574645996, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/6f854997d8d106f089ed82af86794ddd48a1326fa3e6ef69b74bc068eb7856d3.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": "700a719561d023158844d62673c78605d84ae26cd5938dd53a66fd15bbb28340", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5fe8169745b5faba407e764cc36f4d4d86c4baedf5192832ca8693e1c5b1cc29", "generation_seconds_batch": 16.230300738010556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9131455421447754, "target_z": 1.609375021395695, "ce": 6.054384231567383, "genuineness": 4.093128204345703, "identity": 0.5906851291656494, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/700a719561d023158844d62673c78605d84ae26cd5938dd53a66fd15bbb28340.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": "7024cd9c8c130b685fd79f8d67be34975c448d1a4eaccb09274b70139958802a", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8572e3575f7a30858b724d58eb5a646a29e60ab736f7b61476b5b05f89783a9", "generation_seconds_batch": 17.001222103019245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.663196563720703, "target_z": 1.3359373537960837, "ce": 6.109982967376709, "genuineness": 4.18099308013916, "identity": 0.6090537905693054, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7024cd9c8c130b685fd79f8d67be34975c448d1a4eaccb09274b70139958802a.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "70c3dace798ce2c99f55889ea3952676727d6d6a84e0605f40d8bcc9246732b0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7c8adae4979564e9af3dfda23e82bf6b112f9dab486f5bbe22c500597ad7d89a", "generation_seconds_batch": 19.37749345100019, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7274692058563232, "target_z": 1.4062499490578688, "ce": 5.990842819213867, "genuineness": 4.030367851257324, "identity": 0.5975394248962402, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/70c3dace798ce2c99f55889ea3952676727d6d6a84e0605f40d8bcc9246732b0.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "70edf01dbf48125211f6f5c0661ae929d91f35e5cf09b47b0e44fc17ad8a417d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f88b3cadbf88fcb59e8cd8dcabda0268eb77a5a04bdc92aef4297b2e1872a61c", "generation_seconds_batch": 20.271886563976295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.241854429244995, "target_z": 0.8750000407537049, "ce": 6.181467056274414, "genuineness": 3.9927117824554443, "identity": 0.6091821789741516, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/70edf01dbf48125211f6f5c0661ae929d91f35e5cf09b47b0e44fc17ad8a417d.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": "70f9361163142229ee5871d46d9e01fec4522cf41b0be9e9e184fc8179cb73fe", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15b24df4cb2a083b58f68739d7f5a3fe94c25b323dc0f36f71c696319f57686d", "generation_seconds_batch": 15.497880470007658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2204301357269287, "target_z": 0.8515624220585394, "ce": 6.205295085906982, "genuineness": 4.400654315948486, "identity": 0.6262732744216919, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/70f9361163142229ee5871d46d9e01fec4522cf41b0be9e9e184fc8179cb73fe.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "71dca418b7c5843c9365f5a1bf8269c965adbf64419d31381927bd77469c5ab9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f0cf111a4f0c320e40e22c1640efb9c68a9ffff32cc9aa0bea6de0bd9d619a8c", "generation_seconds_batch": 23.319186892011203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4418134689331055, "target_z": 1.0937500183391673, "ce": 6.348263263702393, "genuineness": 4.469690799713135, "identity": 0.5303781032562256, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/71dca418b7c5843c9365f5a1bf8269c965adbf64419d31381927bd77469c5ab9.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "7212d366d12208965c8490b47e8752923df7323e052beccf2cb1396836d79020", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c918651a589e24698249c4838b132f4b309fc22e09b2d30afedb4dcd7b44d660", "generation_seconds_batch": 19.822595144971274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.770317554473877, "target_z": 1.4531249256244885, "ce": 6.165581703186035, "genuineness": 4.293961524963379, "identity": 0.36814451217651367, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7212d366d12208965c8490b47e8752923df7323e052beccf2cb1396836d79020.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "72c04d0f828c9091dd8dc87818d9c87e5da5fd4f749bf3fc4e8b800d50108acf", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6f190093e08d129fbdecb8ba90371de389cb749d1518a1d6509fe0ddb47e62bb", "generation_seconds_batch": 20.328406741959043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.47752046585083, "target_z": 1.1328125422819688, "ce": 6.197352409362793, "genuineness": 4.256305694580078, "identity": 0.22539794445037842, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/72c04d0f828c9091dd8dc87818d9c87e5da5fd4f749bf3fc4e8b800d50108acf.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": "7345c7dbd3e3ac77b29014c628cfaa1560e41aa0cb7b664d0b55e5f5732cb1ca", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a2df9ab2321484dab1f4ac2edcbb00276f31bc2e32a86d6860edb8a339c376a", "generation_seconds_batch": 14.73156733601354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7346105575561523, "target_z": 1.414062401681687, "ce": 6.078212261199951, "genuineness": 4.005263805389404, "identity": 0.399696946144104, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7345c7dbd3e3ac77b29014c628cfaa1560e41aa0cb7b664d0b55e5f5732cb1ca.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "734ceb42d77282f2c79a714d7f88892deee0ca7f5db090e879f6e9ba056656a6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f0b1bc25b523e8c8bc4d80f3e3d134a55a3597b92cf9233a7180aca1557c1cf9", "generation_seconds_batch": 17.11892961594276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7560348510742188, "target_z": 1.4375000203768524, "ce": 6.038498878479004, "genuineness": 4.017816066741943, "identity": 0.07863662391901016, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/734ceb42d77282f2c79a714d7f88892deee0ca7f5db090e879f6e9ba056656a6.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "739db5c384c9093d7c57e6d2c9ba789c22e77f8faebb2a4477e9625a318bd6a1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6c4b6455472e7c0668dab6f5a16c69fd99963fceb33773f11111e019cd041555", "generation_seconds_batch": 15.242760193999857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0274078845977783, "target_z": 1.734375045847918, "ce": 6.300607204437256, "genuineness": 4.337893962860107, "identity": 0.42078620195388794, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/739db5c384c9093d7c57e6d2c9ba789c22e77f8faebb2a4477e9625a318bd6a1.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "73b9e7085bba917804765f572393daf400685ddaa61998251eb7b7c8c512a3b9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "82e9c319441d356be6e4c63f7f0d77e1c5f2175c68efa4194cc22b857d770c22", "generation_seconds_batch": 21.80314856301993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.891721248626709, "target_z": 1.5859374027005295, "ce": 5.760505676269531, "genuineness": 3.961331605911255, "identity": 0.36656200885772705, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/73b9e7085bba917804765f572393daf400685ddaa61998251eb7b7c8c512a3b9.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "7405ef8152590dfba873eddd1ab81f39a1ab5f7bc515964428404a7721a807b4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "007e12c8b907fd0f618a0cf381f50af1518b9fce77b684f780fecc1d23347e77", "generation_seconds_batch": 20.955746807041578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1490163803100586, "target_z": 0.7734376349966474, "ce": 6.038498878479004, "genuineness": 4.149612903594971, "identity": 0.5269981622695923, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7405ef8152590dfba873eddd1ab81f39a1ab5f7bc515964428404a7721a807b4.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "7428944a8b8db6e90e29bf3dbbb5080f37712c87999ce630b92e5652f5b3410d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "460b18cc9b8f27f914f99213bcc85709e1385208b2bf0feebc97278c3e2e273e", "generation_seconds_batch": 20.233025470981374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.063114643096924, "target_z": 1.7734373089670084, "ce": 6.23706579208374, "genuineness": 4.193545341491699, "identity": 0.5030014514923096, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7428944a8b8db6e90e29bf3dbbb5080f37712c87999ce630b92e5652f5b3410d.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "74db363e56abbb709012f53041baff54477f9c6b813928c77e470b24495e917f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4217bc92f68708d3d9fa285c56853121423a729bf13cdade09dd8b8633ed9f1b", "generation_seconds_batch": 24.755143972928636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.181467056274414, "genuineness": 4.532451152801514, "identity": 0.6078200340270996, "hypothesis": "La porte est encore ouverte! J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Ah !", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/74db363e56abbb709012f53041baff54477f9c6b813928c77e470b24495e917f.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": "753668159bff77dbf5eb2e885ae64c22a5ec715cdf5c5d29026f25ebdc9c9f3e", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4c0024796dcdcff655d8d9a0faf89cf019ea1f05c1ab96caf0f42fdd55bbc0a", "generation_seconds_batch": 20.645170028088614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9276330471038818, "target_z": 0.5312500387160196, "ce": 6.181467056274414, "genuineness": 4.362998008728027, "identity": 0.7260271906852722, "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/753668159bff77dbf5eb2e885ae64c22a5ec715cdf5c5d29026f25ebdc9c9f3e.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": "759f8c829df3b0b4c959b77d254e95dd8370eb677b53a8d981990fdeae56310d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "507838043991d7ef2df148d58c68a55d0cdabb4877c536eefef6a48edbe240b9", "generation_seconds_batch": 15.52198843297083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.955993890762329, "target_z": 1.6562499979623146, "ce": 6.284721851348877, "genuineness": 3.911123275756836, "identity": 0.6059491038322449, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/759f8c829df3b0b4c959b77d254e95dd8370eb677b53a8d981990fdeae56310d.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "75a356ab8592f7432a32a442cbc7842000a4f6419dd633c95397f34e0fe5b54a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "10fda6b3c2dbe5c53d4970eaf36f51c591aa4139d9817588c7a798738a388774", "generation_seconds_batch": 20.552334274048917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7346105575561523, "target_z": 1.414062401681687, "ce": 6.23706579208374, "genuineness": 4.381826400756836, "identity": 0.7025290727615356, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/75a356ab8592f7432a32a442cbc7842000a4f6419dd633c95397f34e0fe5b54a.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "75c793bdb02e0582028cc6826447caebb92b0d3b93d25d5c56ea9dc71912ab1a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f9d7a85483648caef2997ef0234aefe2c5b8266b3fadfeeb0f1b8a725fafed75", "generation_seconds_batch": 20.133414746029302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.752668857574463, "target_z": 0.33984377572577623, "ce": 6.038498878479004, "genuineness": 4.319066047668457, "identity": 0.6604057550430298, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/75c793bdb02e0582028cc6826447caebb92b0d3b93d25d5c56ea9dc71912ab1a.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "76257fe8bc157de32554ca8299196996a65572cabfbd452fa5eb29e4aa352210", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "44368cc7ce8f2cda7258f2d5d3d25351080ee5e4ffb6660cbffc5d94da7ac21f", "generation_seconds_batch": 19.66208574094344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.227571487426758, "target_z": 0.8593748746823575, "ce": 6.197352409362793, "genuineness": 4.557555198669434, "identity": 0.616304874420166, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/76257fe8bc157de32554ca8299196996a65572cabfbd452fa5eb29e4aa352210.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": "774d46561a8e2a3081c57f44b35ba3d08dbb9d9ac0713b40a839a0cfbc6184cc", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "44331c037575a28b68c78bd9359f0f818537eb96836963b1ecd00af1bdcca8d4", "generation_seconds_batch": 16.977139194961637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7488932609558105, "target_z": 1.429687306929323, "ce": 6.252951145172119, "genuineness": 4.18099308013916, "identity": 0.4567795693874359, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/774d46561a8e2a3081c57f44b35ba3d08dbb9d9ac0713b40a839a0cfbc6184cc.mp3" }, { "id": "heldout-fr-3", "language": "fr", "sentences": [ "Quelqu’un a déplacé la petite chaise bleue.", "Elle était ici... près de la grande bibliothèque.", "Nous la remettrons après le déjeuner." ], "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-3", "key": "77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Intense Interest. 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": "d91768a3076c392fcd4f834ce3f36c975d8467fa569c9979df3661874822f0f7", "generation_seconds_batch": 17.244187982054427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4489548206329346, "target_z": 1.1015624709629852, "ce": 6.23706579208374, "genuineness": 4.444586753845215, "identity": 0.7121666669845581, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue, elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "781ed35d432d4cbc9aacfced9d9628f96ed81d50263a456a1646d6a2b7a7616b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "699cbe62f2a42acd2d9d3a7a516b46fd39bef305a4a89e66e43d3d81eeb59939", "generation_seconds_batch": 20.7474313180428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9883348941802979, "target_z": 0.5976562772540401, "ce": 6.284721851348877, "genuineness": 4.093128204345703, "identity": 0.4883316457271576, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/781ed35d432d4cbc9aacfced9d9628f96ed81d50263a456a1646d6a2b7a7616b.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "78b3a3e425ae27a03921003181f7fc6bd6b41ff8dedf732c7d92cdfe151b5c14", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "eccb90bef7f4bf35a72118fe21619ce037518a131bde4b1ea4493a55b356b3e3", "generation_seconds_batch": 19.86970088700764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.88457989692688, "target_z": 1.5781249500767116, "ce": 6.23706579208374, "genuineness": 4.262581825256348, "identity": 0.42967987060546875, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/78b3a3e425ae27a03921003181f7fc6bd6b41ff8dedf732c7d92cdfe151b5c14.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "78d4265ba2ee956fca8e65f7e7d1318efab5663818455bb2d019576601266f83", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "366ec19b36ba946ad32f8160016994dc435da120d30449749065a14324d78d14", "generation_seconds_batch": 21.36969505401794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.527510166168213, "target_z": 1.1874999714724066, "ce": 6.1894097328186035, "genuineness": 4.507347106933594, "identity": 0.7126314640045166, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/78d4265ba2ee956fca8e65f7e7d1318efab5663818455bb2d019576601266f83.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "7938d2dfb4f9c31aa43513c59df790da2c75058fe5836efbee80a03b2ff9f837", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cdc7d6dad80fd8cdebcdfd4ee82728640d4ab98fe8e45c99474cdd5d1baa06bb", "generation_seconds_batch": 20.689047247054987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4416089057922363, "target_z": 2.18750016709019, "ce": 5.585766792297363, "genuineness": 4.030367851257324, "identity": 0.4745815098285675, "hypothesis": "¡La puerta sigue abierta! He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7938d2dfb4f9c31aa43513c59df790da2c75058fe5836efbee80a03b2ff9f837.mp3" }, { "id": "heldout-nl-1", "language": "nl", "sentences": [ "De sleutels liggen op de keukentafel.", "Ik keek in de la... en daarna naast het raam.", "Neem ze mee als je weggaat." ], "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-1", "key": "794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Intense Interest. 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": "696f9814e6f990a412edd0942cc5246c601e0d8b6976e6a20b9df0877dcd883e", "generation_seconds_batch": 16.859554570983164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5132274627685547, "target_z": 1.1718750662247703, "ce": 6.125868320465088, "genuineness": 4.080576419830322, "identity": 0.5725404024124146, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het draam, neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "79821d4093ba65acffb1a3c3e959c6512de0f8704b00f4e4055ed17b4f44e10e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "442c06191639637253b7eb2f1189b29ffefe9bc63212415c01cce4e7758c6410", "generation_seconds_batch": 21.157516070990823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5130228996276855, "target_z": 2.265625214975793, "ce": 6.117925643920898, "genuineness": 4.3504462242126465, "identity": 0.411234974861145, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/79821d4093ba65acffb1a3c3e959c6512de0f8704b00f4e4055ed17b4f44e10e.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "79dc8e0753756ec6e02001ce899f3e87c3d4d9ec38c4e5bcd39979b916c7bb67", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5ef63c8975ae8333557f847bbe8a13edebdc555ec80e4f7dbb69ac8aede006ac", "generation_seconds_batch": 20.202797116944566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.34897518157959, "target_z": 0.9921873517583985, "ce": 6.109982967376709, "genuineness": 4.507347106933594, "identity": 0.549735426902771, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/79dc8e0753756ec6e02001ce899f3e87c3d4d9ec38c4e5bcd39979b916c7bb67.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "7a31f0ece82719d213315859def3e9010e92f3fe2d3fc22f843e5655f10dec60", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7f03308e7fd75810f8b78053148a387fd79883d3cca45a293559d3c989a4474e", "generation_seconds_batch": 20.475317662931047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.827653408050537, "target_z": 0.42187491951143286, "ce": 6.213237762451172, "genuineness": 4.6956281661987305, "identity": 0.561233639717102, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7a31f0ece82719d213315859def3e9010e92f3fe2d3fc22f843e5655f10dec60.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": "7ad4876677637d45dc89d42e4ba508761488250ef8ec54c8f27512ac46206373", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fa4d11c6c44ebb5908591188808077ea94291a1ae3bafccdd3f3c27ca335fc2", "generation_seconds_batch": 15.576037400984205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.841731548309326, "target_z": 1.5312499735100917, "ce": 6.435632705688477, "genuineness": 4.218649387359619, "identity": 0.416062593460083, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7ad4876677637d45dc89d42e4ba508761488250ef8ec54c8f27512ac46206373.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "7b5370e26f47fa35bfe0ffb692af018894504e6718da8d5783e42b9b2118a8fc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "525c30c5d3bf80f876d191cf0d25d9c194d73310ab812cf860aac76070ed66fb", "generation_seconds_batch": 15.052944983006455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.070460796356201, "target_z": 0.6874998736635148, "ce": 6.133810997009277, "genuineness": 4.482243061065674, "identity": 0.6184861660003662, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7b5370e26f47fa35bfe0ffb692af018894504e6718da8d5783e42b9b2118a8fc.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "7b639b8871eeccff746f6c07c87d5a02cfcdbe115fdd1cae8318a2a0f0c86a13", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3ddc11a4c67373acc88f1d40d0ad0e986b48eb1ed836534ebd406224b8a8583c", "generation_seconds_batch": 24.46550685900729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5489344596862793, "target_z": 1.210937590167572, "ce": 5.959072113037109, "genuineness": 3.4937667846679688, "identity": 0.562323808670044, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7b639b8871eeccff746f6c07c87d5a02cfcdbe115fdd1cae8318a2a0f0c86a13.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "7c624c6f3e84c4c967e018d41462d6da1749986a3f71ea97daac3d42ae17e010", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "92573cad5a10215cf96bb537ba95681ce78bff28ac4c53520757ac00d54be969", "generation_seconds_batch": 21.960686126025394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6986989974975586, "target_z": 2.468750026489908, "ce": 5.792276382446289, "genuineness": 4.143336772918701, "identity": 0.5825242400169373, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7c624c6f3e84c4c967e018d41462d6da1749986a3f71ea97daac3d42ae17e010.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": "7cdb8a368bb8e30cf4f6530b20eb3b3518bc2917baff6ba794f4abf47f522522", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "298bcacc8cd99465f68ba143e126636a9c9fdd40528fec5cb4450b24d2a79ed7", "generation_seconds_batch": 20.931585252983496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.898862838745117, "target_z": 1.593750116148059, "ce": 6.41180419921875, "genuineness": 4.6705241203308105, "identity": 0.5840837955474854, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7cdb8a368bb8e30cf4f6530b20eb3b3518bc2917baff6ba794f4abf47f522522.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": "7d31ac45ad1c55ae129a1d14b7df85d29a1ac44ecbb348c3183e716878cfe4c2", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da84ec7b499747f43aab550a72e01ae6d43b04ad6d8c415c0851647879866b5c", "generation_seconds_batch": 15.351007401011884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.17401123046875, "target_z": 0.8007813495918663, "ce": 6.221180438995361, "genuineness": 4.20609712600708, "identity": 0.6172611117362976, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7d31ac45ad1c55ae129a1d14b7df85d29a1ac44ecbb348c3183e716878cfe4c2.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "7d3e139eed47ec80b357a4e363ed80aef0c85f0846a71585f225e409dfed7f5e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "53104ae730e3eb12bbab25b7237503df47b970db322ee7af62c22f75556d5f02", "generation_seconds_batch": 15.215991965029389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.363258123397827, "target_z": 1.007812517829746, "ce": 6.221180438995361, "genuineness": 4.2751336097717285, "identity": 0.5341030955314636, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7d3e139eed47ec80b357a4e363ed80aef0c85f0846a71585f225e409dfed7f5e.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "7dd51586f32d78316ee50417c6cbd5c8269cbb5d039815cc264e6e72d620cce1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "238b0c5caa99896ec50edcb7a6e5110eb1ce84752dd7fb27c6a9c192c0e2ff5d", "generation_seconds_batch": 20.19185280392412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.070256233215332, "target_z": 1.7812500224145378, "ce": 6.109982967376709, "genuineness": 4.042920112609863, "identity": -0.09899784624576569, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7dd51586f32d78316ee50417c6cbd5c8269cbb5d039815cc264e6e72d620cce1.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "7e3b4a29539962fcb0b809bb244c257b4d3ccccb327564702b7ec47c18aaee66", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "67aa9db6f118675a8b15496fc1a896c1dfc6c5e414d63d73fb1cc3072959d14c", "generation_seconds_batch": 21.757493808981963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9274282455444336, "target_z": 1.6249999266433313, "ce": 5.831989288330078, "genuineness": 3.7165660858154297, "identity": 0.4482967257499695, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7e3b4a29539962fcb0b809bb244c257b4d3ccccb327564702b7ec47c18aaee66.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "7e534a8d0ce7c74ab797497476bc179d11839f5a9bdfdbb691ecf2b7c7370332", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "faffefcc473ef5d1c675fdab603978452fd1d4ca7fbce6f4c9f669d900a5f427", "generation_seconds_batch": 20.30470326996874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8631558418273926, "target_z": 1.5546875922052572, "ce": 6.260893821716309, "genuineness": 4.086852550506592, "identity": 0.4294883906841278, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7e534a8d0ce7c74ab797497476bc179d11839f5a9bdfdbb691ecf2b7c7370332.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": "7e97eb2f92d9a7aec4c8b8b75d4ed12dd280dfe412174a523f1d54937b77dd65", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89240fea68ae849a274071da2f566055bcffd755452047d8e10a8432e5feec1b", "generation_seconds_batch": 21.008579100947827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.784600257873535, "target_z": 1.4687498308721247, "ce": 6.41180419921875, "genuineness": 4.362998008728027, "identity": 0.35380658507347107, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7e97eb2f92d9a7aec4c8b8b75d4ed12dd280dfe412174a523f1d54937b77dd65.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "7eaf0a271c5b92ce5ec6b8642d989dde64f27e67f09102aa1c97d941a067e9af", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8d14387c6b5e0ae1b046b5f138a41f278049b54bf97b7ba147c9bfbfdc6bef45", "generation_seconds_batch": 15.441131678991951, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3168389797210693, "target_z": 0.9570311845393615, "ce": 6.38003396987915, "genuineness": 4.036643981933594, "identity": 0.516941249370575, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7eaf0a271c5b92ce5ec6b8642d989dde64f27e67f09102aa1c97d941a067e9af.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "7ed4ac5b51bc385f4612b4d92b7f33ad48febdfc1eda77bdec67a5bbea52c1d9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "692d3017255a6e7471226cb7400c0c82dcd84fd2d5d3905024080cf3c2714f76", "generation_seconds_batch": 20.880165035952814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2130842208862305, "target_z": 1.937500118185744, "ce": 6.141753673553467, "genuineness": 4.381826400756836, "identity": 0.4722493588924408, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7ed4ac5b51bc385f4612b4d92b7f33ad48febdfc1eda77bdec67a5bbea52c1d9.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": "7eecb4b546025f93b161e40d85b528781c7be17020130dbca919f2734e55fe16", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d1d0cea1733cc47ed7b1c33fd1dc2a82e52cb718318e4ea55e4a3dd7465e061", "generation_seconds_batch": 20.57794175692834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.484661817550659, "target_z": 1.140624994905787, "ce": 6.1894097328186035, "genuineness": 4.494794845581055, "identity": 0.7623047828674316, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7eecb4b546025f93b161e40d85b528781c7be17020130dbca919f2734e55fe16.mp3" }, { "id": "heldout-en-1", "language": "en", "sentences": [ "The keys are on the kitchen table.", "I checked the drawer... then looked beside the window.", "Take them with you when you leave." ], "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-1", "key": "7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Intense Interest. 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": "12cb8beed425f889cbbdebd3065ee3c2af5fdd9787d61c3eca24b79be1a37ad7", "generation_seconds_batch": 17.729181260918267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4346721172332764, "target_z": 1.0859375657153492, "ce": 6.348263263702393, "genuineness": 4.15588903427124, "identity": 0.30030232667922974, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "7f731697de50729eb3fb52319f4e0a9d8951f26b89bbaa011412b2c4cd27b138", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "445c65ed2f60c567080c88d67c6af752ef752158b8ac090b1a5987c71cab74d0", "generation_seconds_batch": 20.86182191304397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3132684230804443, "target_z": 0.9531250886393081, "ce": 6.3641486167907715, "genuineness": 4.6956281661987305, "identity": 0.5257999897003174, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7f731697de50729eb3fb52319f4e0a9d8951f26b89bbaa011412b2c4cd27b138.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "7f9820ecbcbd493235dfddebd9f9651950d0f3709ec2f6b45b9042473308d99c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "62c48769a77f03217c55d087b47d5ae5629a968fa31fb2ab761e548e2a69819b", "generation_seconds_batch": 16.585141211980954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.406106472015381, "target_z": 1.0546874943963656, "ce": 6.308549880981445, "genuineness": 4.362998008728027, "identity": 0.36071693897247314, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand heute neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7f9820ecbcbd493235dfddebd9f9651950d0f3709ec2f6b45b9042473308d99c.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "7fb5a671c140cb245f9e61451980559d3691119d70ed68c6c30efe0ded0e53a1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6e3b8d03d8d09316e7f8c3f6c3f9905f3fd21e24765b52a75e67d1c1b589d149", "generation_seconds_batch": 22.45881299697794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.955993890762329, "target_z": 1.6562499979623146, "ce": 6.300607204437256, "genuineness": 4.243753433227539, "identity": 0.4757421314716339, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7fb5a671c140cb245f9e61451980559d3691119d70ed68c6c30efe0ded0e53a1.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "7fc710fdd0905741d44dd3df155ecc04375c1c7d5757ded184ab17d083ed419a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "06609b6809b01cf00e780cc57427bd00cbdd3bcc78b38661066d39b340cb5c56", "generation_seconds_batch": 20.770266088075005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4989447593688965, "target_z": 1.1562501609771343, "ce": 6.117925643920898, "genuineness": 4.337893962860107, "identity": 0.5234419107437134, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7fc710fdd0905741d44dd3df155ecc04375c1c7d5757ded184ab17d083ed419a.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "7fff7791e1c741644c25698b533eff7c783a0e5a92ccd073f4e88b07613dbd3d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1e7fadb3c9c3d03ccba27427dd5566ea8f332cce0ef82d0058c9350878832c69", "generation_seconds_batch": 20.486618498922326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.463237762451172, "target_z": 1.1171876370343328, "ce": 6.268836498260498, "genuineness": 4.532451152801514, "identity": 0.5179656147956848, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/7fff7791e1c741644c25698b533eff7c783a0e5a92ccd073f4e88b07613dbd3d.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "800c9575d20b9cc0ef4281e79b080da5603dd68022036b9f5907043e1ef5c5de", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "085bc7edb8a7fe45f95a4dc4f58abd149b11f1b6d94339034f1dec7a45ee4ed3", "generation_seconds_batch": 19.692197527037933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.770317554473877, "target_z": 1.4531249256244885, "ce": 6.395919322967529, "genuineness": 4.055472373962402, "identity": 0.495849072933197, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/800c9575d20b9cc0ef4281e79b080da5603dd68022036b9f5907043e1ef5c5de.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "800e546b64f6d71ff7ee5f6b63f57cc2799f9003b9478b19c3cd0bf5023eefc5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "138d54d57ecb76b24f504c45ec210ac020a01885552280dddf1e0ff026f80580", "generation_seconds_batch": 24.022898443043232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0347537994384766, "target_z": 0.6484373497207132, "ce": 6.197352409362793, "genuineness": 4.394378662109375, "identity": 0.5329779386520386, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/800e546b64f6d71ff7ee5f6b63f57cc2799f9003b9478b19c3cd0bf5023eefc5.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "802bb1e5c564aa78a09132bda4fbd5604f7ff997db6bc2c1f8e29414661bd2a4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "78264be23ab810b5af55c44a8ead35c6a3a45e0c359b6504f9f8b7f1be50d823", "generation_seconds_batch": 19.910861787036993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.166869640350342, "target_z": 0.792968636144337, "ce": 6.157639026641846, "genuineness": 3.8044304847717285, "identity": 0.4339725077152252, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/802bb1e5c564aa78a09132bda4fbd5604f7ff997db6bc2c1f8e29414661bd2a4.mp3" }, { "id": "heldout-es-1", "language": "es", "sentences": [ "Las llaves están en la mesa de la cocina.", "Miré en el cajón... y luego junto a la ventana.", "Llévatelas cuando te vayas." ], "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-1", "key": "80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Intense Interest. 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": "b8c6e75c31422a6af079a5fa311893b44a579c394519d41780fb6b4029aa865a", "generation_seconds_batch": 15.480531389010139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.288273334503174, "target_z": 0.9257811132203779, "ce": 6.356205940246582, "genuineness": 4.400654315948486, "identity": 0.5283713340759277, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "80f54b622551909dc804253b244c878647ed23b0711f4647f41bf4090bfde9cb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2e51fb65f94775319d82056c0979caa1bc8e0c14091f953c03312c366647d74b", "generation_seconds_batch": 15.052944983006455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.291844129562378, "target_z": 0.9296874699441426, "ce": 6.181467056274414, "genuineness": 4.243753433227539, "identity": 0.521895706653595, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/80f54b622551909dc804253b244c878647ed23b0711f4647f41bf4090bfde9cb.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "80f5ad05aa0150bde351203b73d6389633071f127a5f595ccf371585292471de", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7f7549b8ec01311327a173d81c311ed9613a5cfde2d417be85d837b2d9a532d0", "generation_seconds_batch": 20.213153827004135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8702971935272217, "target_z": 1.5625000448290753, "ce": 5.998785495758057, "genuineness": 4.137060642242432, "identity": 0.4870743155479431, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/80f5ad05aa0150bde351203b73d6389633071f127a5f595ccf371585292471de.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "813cc858164dfd4ab29c8f4b3b55a7cd48bf419c7245389f81160f844053dfa7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d303ba42e3b62341de14cf6255721b1a0be322f88a9c489b2572d522a09575f8", "generation_seconds_batch": 21.031932740006596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.648913860321045, "target_z": 1.3203124485484476, "ce": 6.149696350097656, "genuineness": 4.545003414154053, "identity": 0.5876513719558716, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/813cc858164dfd4ab29c8f4b3b55a7cd48bf419c7245389f81160f844053dfa7.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "8204a8e20c0e6ac62bd1117edc3a96198bea0137431c8a806b763ad62e17aca7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cdb0e68e8ab9d463933e12371bc1aa4bcf380d6a3aaf59a68bbcf939006b0eb4", "generation_seconds_batch": 23.63954745500814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5560758113861084, "target_z": 1.2187500427913902, "ce": 5.692992687225342, "genuineness": 3.911123275756836, "identity": 0.5211321711540222, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8204a8e20c0e6ac62bd1117edc3a96198bea0137431c8a806b763ad62e17aca7.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "8330845451b4ff8278cb11568f196a0bbcc246a88add302ebd90ddbbb4366923", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "164c3d9d6ee42fb0129b0c8e2d3963af299def0446c00d8f1694a8f8d8c30bca", "generation_seconds_batch": 19.860008836956695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8560142517089844, "target_z": 1.546874878757728, "ce": 6.125868320465088, "genuineness": 4.030367851257324, "identity": 0.621550440788269, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8330845451b4ff8278cb11568f196a0bbcc246a88add302ebd90ddbbb4366923.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "8447a91fff6bf033c65a702a249496e12a19d2f88884f5f31b1b15a8e2125421", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7b50ca530ed26a5fcb21fec754fb8bab60d6b84ebc04feaf5f691de70bd00b1c", "generation_seconds_batch": 21.121698254952207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7988831996917725, "target_z": 1.484374996943472, "ce": 5.403085231781006, "genuineness": 3.747946262359619, "identity": 0.37528371810913086, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8447a91fff6bf033c65a702a249496e12a19d2f88884f5f31b1b15a8e2125421.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "8448d05d3594faeb06f1e5b7f81a0bc950361b3c7b6432597ff8495e83b35337", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "24958cb6bb96ff1323c021d2533d4ff66e247a0cfa9646d53df43bea89f301f2", "generation_seconds_batch": 21.613487274968065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2630739212036133, "target_z": 1.9921875473761819, "ce": 5.597680568695068, "genuineness": 4.005263805389404, "identity": 0.41114142537117004, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8448d05d3594faeb06f1e5b7f81a0bc950361b3c7b6432597ff8495e83b35337.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "853ecd3bee1d2de56ddaff6fb4cdbf53069e89cc78647fbdad6675e57b025fb8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e20acf1bdec076849c75bb48ce52144928b3023d642a4660c2e3c3ae97ec9a96", "generation_seconds_batch": 19.80117143294774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8129611015319824, "target_z": 2.59374979011842, "ce": 5.760505676269531, "genuineness": 4.105680465698242, "identity": 0.42686671018600464, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/853ecd3bee1d2de56ddaff6fb4cdbf53069e89cc78647fbdad6675e57b025fb8.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "85df50db8706a3c51cb3bb5fafa06a1d153f8bca09de63eea24209767d885340", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "38983ea7353f8701e8e3da21c1302386fba39f815943062cc7e58918987cf9dc", "generation_seconds_batch": 15.467794907046482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.877438545227051, "target_z": 1.5703124974528935, "ce": 6.205295085906982, "genuineness": 4.6956281661987305, "identity": 0.5934739112854004, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/85df50db8706a3c51cb3bb5fafa06a1d153f8bca09de63eea24209767d885340.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "86ac71857eeafc814d067e32cdb1f3308c11e94cdfbd7e6303519300bc9da1b4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a3b6ea0905721162e986e3bcb77ae6a1fcc0e56939cc21e7a14ada91ed067890", "generation_seconds_batch": 21.674231372075155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6203484535217285, "target_z": 1.2890626380531753, "ce": 5.967014789581299, "genuineness": 4.055472373962402, "identity": 0.06911520659923553, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/86ac71857eeafc814d067e32cdb1f3308c11e94cdfbd7e6303519300bc9da1b4.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": "86f38fd61ab20af7cbfa19d5f41cd14887cf07fda8c6168410ce78214271baaa", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c2932693570766f454f349ee99416ce9b8a03663562214e7e1dc662196acf57", "generation_seconds_batch": 20.68333102890756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2273669242858887, "target_z": 1.9531250234333803, "ce": 6.1020402908325195, "genuineness": 4.15588903427124, "identity": 0.3427581191062927, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/86f38fd61ab20af7cbfa19d5f41cd14887cf07fda8c6168410ce78214271baaa.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "86f995e0bad59b11b86efb1acf7f7bc87eb93635dd364268a452f74994262779", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9adb00eaa63ced928860bd06e44ec700c45594ba2c45f05360a7d9f5e3f0b387", "generation_seconds_batch": 22.679797998978756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2811319828033447, "target_z": 0.9179686605965599, "ce": 5.816103935241699, "genuineness": 4.369274139404297, "identity": 0.5916262865066528, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/86f995e0bad59b11b86efb1acf7f7bc87eb93635dd364268a452f74994262779.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "873fd41b544e1269a902926f5c36c51f76ff8b2f5238a95fbc0cc36e79bf4079", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4630e6f25c35bdf6c557f5786fd2e2e2d94b837cc44ccb7805d10c33641c9010", "generation_seconds_batch": 15.084900197922252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.056178092956543, "target_z": 0.6718749684158787, "ce": 6.2767791748046875, "genuineness": 4.400654315948486, "identity": 0.5580415725708008, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/873fd41b544e1269a902926f5c36c51f76ff8b2f5238a95fbc0cc36e79bf4079.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": "874e5041c2d5705dc3cfa058a6ef7df077a50a9417d2d7e1c619830b40b8c2de", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b084a29f860a1e793fd2df2e73b77066c1ebf95453df06fb32fa3fe204c56fb", "generation_seconds_batch": 20.775634670979343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8631558418273926, "target_z": 1.5546875922052572, "ce": 6.0305562019348145, "genuineness": 4.281409740447998, "identity": 0.4729138910770416, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/874e5041c2d5705dc3cfa058a6ef7df077a50a9417d2d7e1c619830b40b8c2de.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": "87da335d9a2cad446282f079da02ab9d1f44a646b2ff75c756ccfddb15dee434", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ddab2d83f712fbb3d87de70f2af4793ff580374e41c5611fbe5078ae8acef5ab", "generation_seconds_batch": 14.79766180505976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2844982147216797, "target_z": 2.0156251660713473, "ce": 6.022613525390625, "genuineness": 4.306513786315918, "identity": 0.5783687233924866, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/87da335d9a2cad446282f079da02ab9d1f44a646b2ff75c756ccfddb15dee434.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "87e510ab670a710c30b82dfbab647d0071620da82ed9888450f2cb7d494d86b5", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "856807769af90a6b47401aded7c4c84231d220ece1b8d30abd3d0aefe3a2da96", "generation_seconds_batch": 16.19399583397899, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2775614261627197, "target_z": 0.9140625646965065, "ce": 6.23706579208374, "genuineness": 4.124508857727051, "identity": 0.4378852844238281, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/87e510ab670a710c30b82dfbab647d0071620da82ed9888450f2cb7d494d86b5.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": "881906e8a38381fee0133b60d95e897dcf84bf4c6da5b8aeab55e0ef9cf39ee3", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I wrote the number on the envelope.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6dff00eb55df5daff91a91ff8498029698cb41e5f0101629ed174aac3503335a", "generation_seconds_batch": 15.36887896899134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2739906311035156, "target_z": 0.9101562079727419, "ce": 6.2767791748046875, "genuineness": 4.005263805389404, "identity": 0.47370707988739014, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/881906e8a38381fee0133b60d95e897dcf84bf4c6da5b8aeab55e0ef9cf39ee3.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": "884eb301f1ceaa1e3cb47667704b3eac58aa52938752984f8772493d2b22a7a7", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9147e3d314fc3cda96913d5757fd1f307d66b81c459d9f13f3c951c80da9b19a", "generation_seconds_batch": 20.931585252983496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5632171630859375, "target_z": 1.2265624954152081, "ce": 6.229123115539551, "genuineness": 4.061748504638672, "identity": 0.3939436972141266, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/884eb301f1ceaa1e3cb47667704b3eac58aa52938752984f8772493d2b22a7a7.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "885c4bc06c63bbf89b5d7270a252eacdf6e198b5cb1d4b6b99dcfc8e4984ac25", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "25261f0cd75f315fb852f90f801c579852678b51a3339ae8c6ad1e3171d9ad14", "generation_seconds_batch": 20.858991027926095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.181152582168579, "target_z": 0.8085938022156843, "ce": 6.173524379730225, "genuineness": 4.293961524963379, "identity": 0.5658280849456787, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/885c4bc06c63bbf89b5d7270a252eacdf6e198b5cb1d4b6b99dcfc8e4984ac25.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "885df816e48d3810fad8a040b8bdfe08afaffb9df540dd2088f1f4d5d0979a95", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "73d9363b971d60e49b01a5f3a700c1c32a367250306d2322e21aafeadcd67e29", "generation_seconds_batch": 22.563913080957718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.641772508621216, "target_z": 1.3124999959246295, "ce": 6.038498878479004, "genuineness": 4.118232727050781, "identity": 0.5735020637512207, "hypothesis": "De deur staat nog open! Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/885df816e48d3810fad8a040b8bdfe08afaffb9df540dd2088f1f4d5d0979a95.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "889c4a73a105455a4dc163018a36932f8f1efc78cc08a31f796d02806861bef7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a7a695596026331a369dc607a9a39afd35e6791bf20e3004ae8ae706f3a114ed", "generation_seconds_batch": 21.28276638209354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.520368814468384, "target_z": 1.1796875188485885, "ce": 6.125868320465088, "genuineness": 4.20609712600708, "identity": 0.6021838188171387, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/889c4a73a105455a4dc163018a36932f8f1efc78cc08a31f796d02806861bef7.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "88eeb83758dfac23f16518f13c86b6f5a5d16d799323983e951204a9d9f55c00", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6057d729a79c241d1c7ffac584584e6fd518291f599cd14db2f30b4490db52a6", "generation_seconds_batch": 16.65475852706004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3311219215393066, "target_z": 0.972656350610709, "ce": 6.41180419921875, "genuineness": 4.375550270080566, "identity": 0.34058713912963867, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/88eeb83758dfac23f16518f13c86b6f5a5d16d799323983e951204a9d9f55c00.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": "891d761202b99fe9e3208c38e99fc02f3ea469a3593502bfa44539e9a9fd0419", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5dd80257f1c5808b7688615ecab21a2c441aa3632d00ab07fc98d50b9a002e7b", "generation_seconds_batch": 20.812772893928923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1630945205688477, "target_z": 1.8828126889953065, "ce": 6.483288764953613, "genuineness": 4.381826400756836, "identity": 0.5410840511322021, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/891d761202b99fe9e3208c38e99fc02f3ea469a3593502bfa44539e9a9fd0419.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "8a192bc4b042b48c691ab5be847835168cdc1f3b51eeba6a8af885a198288709", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4e5176c81822996857d18e4b1085db5b967fb0e99cb5884142db67f6fbebd2cb", "generation_seconds_batch": 20.802370153018273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7241032123565674, "target_z": 0.3085937044067927, "ce": 6.221180438995361, "genuineness": 4.645420074462891, "identity": 0.6638997793197632, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8a192bc4b042b48c691ab5be847835168cdc1f3b51eeba6a8af885a198288709.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "8a1ef72627a5867d1efd418c2328d798d9dbe51e4eb30f61bcb0510143ac8cfd", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "84fefeccfae4fb2b1b340aa0217dd90f8467b50fba9eaa69b371d27e9b427cfb", "generation_seconds_batch": 15.000229672063142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.248995780944824, "target_z": 0.882812493377523, "ce": 6.078212261199951, "genuineness": 4.256305694580078, "identity": 0.4654371440410614, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8a1ef72627a5867d1efd418c2328d798d9dbe51e4eb30f61bcb0510143ac8cfd.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "8a253211d84bb6c6c252203a5160df2d7400ef6cd91a474e7986cf78d4e65e20", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4b558aa3cfd2a4687dca72e60be221563652c8e1fb34603caa76ff04bfbdfd9e", "generation_seconds_batch": 20.424458410940133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4418134689331055, "target_z": 1.0937500183391673, "ce": 6.173524379730225, "genuineness": 4.243753433227539, "identity": 0.5608742833137512, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8a253211d84bb6c6c252203a5160df2d7400ef6cd91a474e7986cf78d4e65e20.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "8afcf55522693f80f41e215d91a9292bd82982889fe143116ff477c4cabe92b1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5f9c6e9c873d910ce9ee7ec08767b3c4ba9c56c4e3113b1545644d68483f5f73", "generation_seconds_batch": 23.078368208021857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.284702777862549, "target_z": 0.9218750173203246, "ce": 6.24500846862793, "genuineness": 4.243753433227539, "identity": 0.5881729125976562, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8afcf55522693f80f41e215d91a9292bd82982889fe143116ff477c4cabe92b1.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "8b00e6598711af0b087b32229002d256cbe834600cd1beab3993b87d7240750c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1628a942034715e562d7540cbd6d2d28d5e58fbb32e41a54b2e2ac65a28c2f9b", "generation_seconds_batch": 21.50847610097844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6703381538391113, "target_z": 1.3437500672436131, "ce": 6.24500846862793, "genuineness": 4.005263805389404, "identity": 0.6091336011886597, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8b00e6598711af0b087b32229002d256cbe834600cd1beab3993b87d7240750c.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "8b323a6e1182aaa0ed24c029bfc5711a0c4918454def349565a511492e90a08a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d233dfb20cf810818a1c8e01024480f96942e3e5b0af89a5af87173061fd0d42", "generation_seconds_batch": 21.053300500032492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5560758113861084, "target_z": 1.2187500427913902, "ce": 6.141753673553467, "genuineness": 4.2751336097717285, "identity": 0.36638200283050537, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8b323a6e1182aaa0ed24c029bfc5711a0c4918454def349565a511492e90a08a.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": "8b6b7709fde7d35e8d18038d48c56ae2d9dea05fa615586b4b96fed503b2c181", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16d6198c2c02bc006ede7d56c089d9b3c7c99748d8659b504be5106fb8b9963b", "generation_seconds_batch": 20.74555579898879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.070256233215332, "target_z": 1.7812500224145378, "ce": 6.252951145172119, "genuineness": 4.093128204345703, "identity": 0.6135263442993164, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8b6b7709fde7d35e8d18038d48c56ae2d9dea05fa615586b4b96fed503b2c181.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "8b990f1bbc0aad4714aea9a24abed4882ae4cb728b9b125f83fa458098d84081", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "692eb02de1cea5fa0ad8f7e47eab611aea8c1129d6032041ec2a571e2dfc01ee", "generation_seconds_batch": 22.460074800997972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302556276321411, "target_z": 0.9414062792917254, "ce": 6.038498878479004, "genuineness": 4.645420074462891, "identity": 0.761894166469574, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8b990f1bbc0aad4714aea9a24abed4882ae4cb728b9b125f83fa458098d84081.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "8baccc92978dab8a3b6cd768594e880ad257d1dfc8f1a4b0d89943baf0e2cc52", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c77b35e9e5eab62ed0aa0ffb25f38e0a173be8774d296722368e7cfa7e24d3e1", "generation_seconds_batch": 20.416274357005022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3061270713806152, "target_z": 0.9453126360154901, "ce": 6.38797664642334, "genuineness": 4.18099308013916, "identity": 0.4426705539226532, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8baccc92978dab8a3b6cd768594e880ad257d1dfc8f1a4b0d89943baf0e2cc52.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "8bf15a09462381cc8a05bc833ed86637e8f76580676988b1616e633a9f9e6df9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "41eb48a434a3f95f5cc4da5b57f73b247b4bc5451c786c6d1fadc9c248265f67", "generation_seconds_batch": 20.126743236905895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2132887840270996, "target_z": 0.8437499694347214, "ce": 6.1894097328186035, "genuineness": 4.394378662109375, "identity": 0.5377404689788818, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8bf15a09462381cc8a05bc833ed86637e8f76580676988b1616e633a9f9e6df9.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": "8c2c0b74a8f69ef9941e2e9b249454f2cf91976fc6cd4981b7555ae5ef783dd6", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I wrote the number on the envelope.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b224ebfa495d65c9964a1a965088aabbec1418100cd4a40ef3a11396fec82ca2", "generation_seconds_batch": 15.26228989311494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.181152582168579, "target_z": 0.8085938022156843, "ce": 6.332377910614014, "genuineness": 3.760498285293579, "identity": 0.4086199402809143, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8c2c0b74a8f69ef9941e2e9b249454f2cf91976fc6cd4981b7555ae5ef783dd6.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "8d014002740d0c16b6554771f610d1f6bd40e0172053d0570d749f7c43158221", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "eec6186ecc16f2fa839b834fc90000f00243d9449e323aadac953bd3927afcfa", "generation_seconds_batch": 20.243690975010395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.052607536315918, "target_z": 0.6679688725158253, "ce": 6.022613525390625, "genuineness": 3.848362922668457, "identity": 0.44800424575805664, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8d014002740d0c16b6554771f610d1f6bd40e0172053d0570d749f7c43158221.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": "8d3fbe683a3c24090ba1135368963be60e9421bb05e24789666ee3701c0c1b11", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The keys are on the kitchen table.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "382b41a76596d78ce84fcb011e178f016ec59c35a2ebeb060575da487e1f4ac4", "generation_seconds_batch": 15.507243506028317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.841731548309326, "target_z": 1.5312499735100917, "ce": 6.1894097328186035, "genuineness": 3.7918784618377686, "identity": 0.27124324440956116, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8d3fbe683a3c24090ba1135368963be60e9421bb05e24789666ee3701c0c1b11.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "8d6f5399c923b115e06a165ed86b094ba47a6d60516c4570e35918eb85e15f21", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dc5b7a688b50990dd067d3ea78ba3bd5ca0804e4c2a59e2761753856adff6815", "generation_seconds_batch": 14.769277616986074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.898862838745117, "target_z": 1.593750116148059, "ce": 6.1020402908325195, "genuineness": 4.2249250411987305, "identity": 0.08337479084730148, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8d6f5399c923b115e06a165ed86b094ba47a6d60516c4570e35918eb85e15f21.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "8d8dc10211a47164263327e34d13c63c462efb2a80a8defe29316f816cb2c5a1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "09f03220bd9831adb0fd80657ea144fb88c795b0e32eb77e51ea77a8a1d09516", "generation_seconds_batch": 15.121650255983695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.827448844909668, "target_z": 1.5156250682624557, "ce": 6.125868320465088, "genuineness": 4.118232727050781, "identity": 0.2397240847349167, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8d8dc10211a47164263327e34d13c63c462efb2a80a8defe29316f816cb2c5a1.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "8e2f21b3566f3af0ae01837e4b8a8c0017132b8c51d2b29391db626899fc13aa", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3af6aaf9ef424ee5290fbb4e2e56b63eb7553e4dee361e4723b999622305a0a0", "generation_seconds_batch": 15.691166584030725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5703585147857666, "target_z": 1.2343749480390263, "ce": 6.157639026641846, "genuineness": 4.017816066741943, "identity": 0.2193908840417862, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8e2f21b3566f3af0ae01837e4b8a8c0017132b8c51d2b29391db626899fc13aa.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "8e373303170b8f161679bd7bde08b2110c1e7a6e225be8705eaa92fb88bf3708", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1726a38ba76a3f0a5e7a5194ab24949252115ac24b5e7e5da9c46695fe9c1497", "generation_seconds_batch": 15.271859729080461, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3987603187561035, "target_z": 2.140624929699859, "ce": 6.221180438995361, "genuineness": 4.21237325668335, "identity": 0.6009725332260132, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8e373303170b8f161679bd7bde08b2110c1e7a6e225be8705eaa92fb88bf3708.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "8e91c2fbe5d1f3dfeb1e132499751f1df1f64bb626f9657745354be56ecf85c5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b30df583ca5b83fedc09528379a3d9edd5b4e28743cc5cd78af0cbf7529cb2b", "generation_seconds_batch": 21.802072854014114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8203072547912598, "target_z": 1.5078123548149263, "ce": 5.792276382446289, "genuineness": 4.068024158477783, "identity": 0.19231213629245758, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8e91c2fbe5d1f3dfeb1e132499751f1df1f64bb626f9657745354be56ecf85c5.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "8eba8952d6ac42c2691272b8fbf137ef7bee6adea31b4e5b04e1353a7360fd59", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b3a8ce6525edad99fbebafbb7a777b45a88ed64b7c1af86f35d8d51d33e110f2", "generation_seconds_batch": 14.96411123604048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4558916091918945, "target_z": 2.2031250723378264, "ce": 6.078212261199951, "genuineness": 4.344170093536377, "identity": 0.5129687786102295, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8eba8952d6ac42c2691272b8fbf137ef7bee6adea31b4e5b04e1353a7360fd59.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "8f28088c18edbc73437abd14b106e46cb9df84fd3a913780d352bae2833125f0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7670aa01ba587eb8f63751dde5590ca13b87c90c341e9fb19c5b989be245e253", "generation_seconds_batch": 21.960686126025394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6844162940979004, "target_z": 2.453125121242272, "ce": 5.657250881195068, "genuineness": 3.9048471450805664, "identity": 0.40912801027297974, "hypothesis": "He encontré la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8f28088c18edbc73437abd14b106e46cb9df84fd3a913780d352bae2833125f0.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "8f63e3a3e37ec7bbe9122403da6432a75492575f850503128dbd3e87fe5a1a9c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "02a4a9c456d58b1e56bf8ea41575637f30b5dd4e9958d2d23cfd904c66cb6b29", "generation_seconds_batch": 19.92497742897831, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9131455421447754, "target_z": 1.609375021395695, "ce": 6.197352409362793, "genuineness": 3.973883628845215, "identity": 0.5688226222991943, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8f63e3a3e37ec7bbe9122403da6432a75492575f850503128dbd3e87fe5a1a9c.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "8f8d3f0a4229861fcf93998b0beed98832c013a66dc232392cb291796a04a2fc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7286b1578050757ef6f2bccb69b4728aaeb81c4e25e56fcc7ecee9900ee1b137", "generation_seconds_batch": 17.11892961594276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0274078845977783, "target_z": 1.734375045847918, "ce": 5.6254801750183105, "genuineness": 3.9048471450805664, "identity": -0.08097543567419052, "hypothesis": "Deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8f8d3f0a4229861fcf93998b0beed98832c013a66dc232392cb291796a04a2fc.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "8fc8cd51c151de30c34dea686a546b5250deeea6c2d6fb9be460cc8173be061c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5ccd0e186a8721623b0ba91f3b244cd3b0715b84bbb0fc9a7ca40ba69e34d529", "generation_seconds_batch": 20.271886563976295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6274895668029785, "target_z": 1.2968748298532822, "ce": 6.260893821716309, "genuineness": 4.7332844734191895, "identity": 0.7143071889877319, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/8fc8cd51c151de30c34dea686a546b5250deeea6c2d6fb9be460cc8173be061c.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "902e4a2cd9acbea9f5f273c44d8f92b64e549a6c9083ef7ef86f407f4295ad86", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "dbe42a540ae948c83d4845cb92c9562b208dfe5ac0c6d76b72b0d1a0ddf2bead", "generation_seconds_batch": 15.052714107907377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.463237762451172, "target_z": 1.1171876370343328, "ce": 6.2767791748046875, "genuineness": 4.017816066741943, "identity": 0.12218156456947327, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/902e4a2cd9acbea9f5f273c44d8f92b64e549a6c9083ef7ef86f407f4295ad86.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "9120626a4979844a1ba0805bf2abd5facf6a3129d1c198aeb98d7bc2bd7b3968", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dfd9b6e97a7c43a756e832d401207f96bad28ce6cd29ca4b730c7845d3404098", "generation_seconds_batch": 25.427187686087564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2130842208862305, "target_z": 1.937500118185744, "ce": 5.990842819213867, "genuineness": 4.15588903427124, "identity": 0.16623446345329285, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9120626a4979844a1ba0805bf2abd5facf6a3129d1c198aeb98d7bc2bd7b3968.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "9177c5d798ef0d2bedce205e4e9f245ad11202a279e95cf045d57c3e2eeb21eb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f5f37feff430d805bbb6fdbcbfe0d887c38ed88f025e6373be369730d1b0f3b", "generation_seconds_batch": 25.427187686087564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0274078845977783, "target_z": 1.734375045847918, "ce": 6.046441555023193, "genuineness": 4.093128204345703, "identity": 0.11006557941436768, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9177c5d798ef0d2bedce205e4e9f245ad11202a279e95cf045d57c3e2eeb21eb.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "918c3e740db4b01245a9b099ae9502541fb07a8df3ad681b669e0f9952ba6a25", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6f557ce3c3a3432e421fc69a774f3f9dcec498158b0dcb45157d8c14d99f1a68", "generation_seconds_batch": 15.330219108029269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4489548206329346, "target_z": 1.1015624709629852, "ce": 6.23706579208374, "genuineness": 4.068024158477783, "identity": 0.30272746086120605, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/918c3e740db4b01245a9b099ae9502541fb07a8df3ad681b669e0f9952ba6a25.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": "91bf5c4c47344d2de69153bb5877c78ac697ae9c13c9f2c862b6a547609b0fa3", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90ccf5d02d5ad43a7c2f2a471032c18479f64c5fd59d5ec150ed7f19394e4f15", "generation_seconds_batch": 15.406588717014529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.852648377418518, "target_z": 0.44921876451850734, "ce": 6.300607204437256, "genuineness": 4.607763767242432, "identity": 0.7863214612007141, "hypothesis": "La route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/91bf5c4c47344d2de69153bb5877c78ac697ae9c13c9f2c862b6a547609b0fa3.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "92f655f16962846918ae7227733f10acb55dac6b07c89f36265f3a8a0cfdd063", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "35f3955952759e49d9822ad2e46b9caa4b090ec0ac154530196042e521f1a8bb", "generation_seconds_batch": 22.204011281952262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 6.427689552307129, "genuineness": 4.099404335021973, "identity": 0.44799742102622986, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/92f655f16962846918ae7227733f10acb55dac6b07c89f36265f3a8a0cfdd063.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": "9345c1ed4defb15d127d06310049915fb96d5c95bc3aa97d7f7d35997625278e", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "877c64e8d297fab6ec2de8148a73c00a67493ccec2340640bd8414cbee1737df", "generation_seconds_batch": 16.977099837036803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9488525390625, "target_z": 1.6484375453384967, "ce": 6.046441555023193, "genuineness": 4.482243061065674, "identity": 0.5502334833145142, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9345c1ed4defb15d127d06310049915fb96d5c95bc3aa97d7f7d35997625278e.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "938a6ff3f83cdb09c95ca4c372d0c2ede3b4284ce81deb8b7ebcbd6852a6d32d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1d6bffba9b73f412037da06346ab6b4925da601154ed1585ba229f25e4378ca6", "generation_seconds_batch": 20.18212297698483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.999047040939331, "target_z": 0.6093750866016229, "ce": 6.2767791748046875, "genuineness": 4.469690799713135, "identity": 0.6043800115585327, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/938a6ff3f83cdb09c95ca4c372d0c2ede3b4284ce81deb8b7ebcbd6852a6d32d.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "93c6c5e20b5f2648349555adb87cfb382721b0f52ec6401ec2afd4c7adc199ad", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "49b9e70c26d5494430e01159ffa81bb8cb1ed15694e310b76615a4a551d9abdf", "generation_seconds_batch": 15.792541157919914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5489344596862793, "target_z": 1.210937590167572, "ce": 5.935244083404541, "genuineness": 4.024092197418213, "identity": 0.09534625709056854, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/93c6c5e20b5f2648349555adb87cfb382721b0f52ec6401ec2afd4c7adc199ad.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "9456bac45a6d9fea2afd91778dca1d93f2f862591d4a1e1f26e8bc05eaf066a5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "585570cdcf24c248a61f012e7b4ed1a83d96561682a5baa24dbc44396cf9b7b7", "generation_seconds_batch": 21.218467638944276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.35591197013855, "target_z": 2.0937499531332393, "ce": 6.340320587158203, "genuineness": 4.268857479095459, "identity": 0.4683721661567688, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9456bac45a6d9fea2afd91778dca1d93f2f862591d4a1e1f26e8bc05eaf066a5.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": "94b47bf12cc31966cf1ef3d891ef24a964619630626b0915dc39dc8e04b2226f", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I wrote the number on the envelope.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4eba40d3da79f056e6e20e54ddbc95e06353c591f79676c65da1249f7d607c1", "generation_seconds_batch": 20.875255957012996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.238283634185791, "target_z": 0.8710936840299403, "ce": 6.316492557525635, "genuineness": 3.8420867919921875, "identity": 0.3312930464744568, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/94b47bf12cc31966cf1ef3d891ef24a964619630626b0915dc39dc8e04b2226f.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "95ab15c2469e60d997659de2625c0bad66885325676f3bee2429c8e240476423", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ee6136ad4a1c5455f8914299c21c1423b8383d3b11a5aec63b336692c5bbf7b3", "generation_seconds_batch": 22.20256691100076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3416292667388916, "target_z": 2.078125047885603, "ce": 6.23706579208374, "genuineness": 4.607763767242432, "identity": 0.6512484550476074, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/95ab15c2469e60d997659de2625c0bad66885325676f3bee2429c8e240476423.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "9610d3624b3fd9b5f33db321c7952c202a358f7d0e1e4edc66bb84beb69cd6c7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5ce2eef3b318cb4b266ef65f1d43f43290125f86d0324462a3cb7e23bc0288d3", "generation_seconds_batch": 19.268706541042775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.134528636932373, "target_z": 1.8515623568526116, "ce": 5.33954381942749, "genuineness": 3.7291181087493896, "identity": 0.407742440700531, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime, ¿cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9610d3624b3fd9b5f33db321c7952c202a358f7d0e1e4edc66bb84beb69cd6c7.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "9719c6a312fa374774dfb5a59bdf6f96de420d8938db473aac9cfeea545073c5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "43de4e781a519f071e383fe3aed12a0c7cf3bbe2fe78d5beecd0faa0d5f21ed0", "generation_seconds_batch": 22.319253675057553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6986989974975586, "target_z": 2.468750026489908, "ce": 5.367343425750732, "genuineness": 4.124508857727051, "identity": 0.3978157937526703, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9719c6a312fa374774dfb5a59bdf6f96de420d8938db473aac9cfeea545073c5.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "9794311ee148a6a2bf8794bde6466cfe49d9468c1705f851d40234ea05b6b20c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5c7defe15845095f5118dda863003b3b85e56b7c2e3e841dfbee864bfc943c13", "generation_seconds_batch": 16.208718682988547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1488115787506104, "target_z": 1.867187522923959, "ce": 5.808161735534668, "genuineness": 3.923675537109375, "identity": 0.5049253702163696, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9794311ee148a6a2bf8794bde6466cfe49d9468c1705f851d40234ea05b6b20c.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "979ec7c41224dbf865a47f45a45f1ce2b864036a8eeee208263f17f973480a7a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e388c48f70fd67d909b912ba2e609516da169af8e39b64dc0878d84cae1a60da", "generation_seconds_batch": 21.571684465976432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.134528636932373, "target_z": 1.8515623568526116, "ce": 6.006728172302246, "genuineness": 4.15588903427124, "identity": 0.2407839596271515, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/979ec7c41224dbf865a47f45a45f1ce2b864036a8eeee208263f17f973480a7a.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "97b8720953b7e15f1755002dc6d6bd7851a2291526b02c31e20d51515afb2cce", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e34118bb850ebd4f5ca7a8c2a72ec6a6d9354f107b6e1688ce5923d0c1af2514", "generation_seconds_batch": 19.921709978953004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5701537132263184, "target_z": 2.328124835966338, "ce": 6.308549880981445, "genuineness": 4.532451152801514, "identity": 0.5180491209030151, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/97b8720953b7e15f1755002dc6d6bd7851a2291526b02c31e20d51515afb2cce.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "97b884335af0d7fe06ccf3aa2c3aac356d048e32a5ca62bcce5a89d9e72e203f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "971ca159435199b101c773b5c435ff12ffafa6586de88c7be7e7704b9f0da437", "generation_seconds_batch": 15.372660969034769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7346105575561523, "target_z": 1.414062401681687, "ce": 5.748591423034668, "genuineness": 3.9048471450805664, "identity": 0.43704545497894287, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/97b884335af0d7fe06ccf3aa2c3aac356d048e32a5ca62bcce5a89d9e72e203f.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "97d9389db7a675483dc5cbc252a927040fc1b3874c5da98f94194e7070548c12", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3ecb0eeee199ff828a63fc08e5625f14c84f941e3dec2a67866700e773a1b724", "generation_seconds_batch": 19.638973752968013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 6.173524379730225, "genuineness": 4.331617832183838, "identity": 0.4686400592327118, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/97d9389db7a675483dc5cbc252a927040fc1b3874c5da98f94194e7070548c12.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "980dd83d4b165c82ad1ada15cd47c997a7c3e37bec87f902ac0e745627198de3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6e87822e815e79a7389802bc5d7f6fe587c0777c6a2994e4b94d6485246fcff2", "generation_seconds_batch": 15.864099674043246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 5.816103935241699, "genuineness": 4.049196243286133, "identity": 0.6018069386482239, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/980dd83d4b165c82ad1ada15cd47c997a7c3e37bec87f902ac0e745627198de3.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": "98468741b9f650d054ef6d5c83716457864b79a8e58210bc7e7e1a883a648404", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4eef03d645748582c0406d43b795d1ee3e5a6e4e29afae73fcd37b4290a87f3", "generation_seconds_batch": 15.402712606010027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7990878820419312, "target_z": 0.39062497860430495, "ce": 6.1894097328186035, "genuineness": 4.482243061065674, "identity": 0.7755835056304932, "hypothesis": "La route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/98468741b9f650d054ef6d5c83716457864b79a8e58210bc7e7e1a883a648404.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": "98ac0b3ad4b472ac07bde9ac0f22b80f4032ac1397dbf6b5ff3c868b9bca132c", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "72560c42059da618e6c4527366c60d6e5657d3c2c92eafd94de54670a946cec9", "generation_seconds_batch": 20.976191518944688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7274692058563232, "target_z": 1.4062499490578688, "ce": 6.173524379730225, "genuineness": 4.557555198669434, "identity": 0.39146891236305237, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter, bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/98ac0b3ad4b472ac07bde9ac0f22b80f4032ac1397dbf6b5ff3c868b9bca132c.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "98eddd99722fc7a770baf16e74b7ee4950a9b14f2c99279954238756001cdd5e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4161a3ca6ac3764e16e99f3d3ce5de938641861656d4f5aa39abc6198e1a38f", "generation_seconds_batch": 14.689185076043941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.077397584915161, "target_z": 1.7890624750383557, "ce": 6.109982967376709, "genuineness": 3.936227321624756, "identity": 0.30422770977020264, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/98eddd99722fc7a770baf16e74b7ee4950a9b14f2c99279954238756001cdd5e.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "990843f60b3784096c3ab30a6103c21fed6796209d137c2762d02b1e519804e6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1887b1624a53a39d2e6a25d24536b99dcda690a9e46a22ee2281550d79a1d05d", "generation_seconds_batch": 20.489954328979366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.298780918121338, "target_z": 2.0312500713189836, "ce": 6.300607204437256, "genuineness": 4.174716949462891, "identity": 0.42218196392059326, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/990843f60b3784096c3ab30a6103c21fed6796209d137c2762d02b1e519804e6.mp3" }, { "id": "heldout-de-0", "language": "de", "sentences": [ "Deine Nachricht kam, als ich schon weg war.", "Ich las sie zweimal... dann legte ich das Handy weg.", "Sag mir, wann wir reden können." ], "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-0", "key": "99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Intense Interest. 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": "37d81705f83beba8086baf56525c6bead01ff831923d23e7d6338f4d1de7ee79", "generation_seconds_batch": 15.946011116029695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.288273334503174, "target_z": 0.9257811132203779, "ce": 6.467403411865234, "genuineness": 4.7332844734191895, "identity": 0.490546852350235, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "9a03ed4d23aad91c1364204fc2eac264dfceb51808fc4e19db2aa8071a7164e4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bd5fceafe054feedd9ac55216794bbf271d70bb2eb31bf9789c9e1ef91bf004c", "generation_seconds_batch": 21.00152736599557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0169005393981934, "target_z": 0.6289063485730237, "ce": 6.205295085906982, "genuineness": 4.2751336097717285, "identity": 0.658314049243927, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9a03ed4d23aad91c1364204fc2eac264dfceb51808fc4e19db2aa8071a7164e4.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "9a1603b89097de7ff1e5b3c78cb1c1ed7af8fbb1a01d505e1e84498a6debd5ef", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6a11ebf4699fc9bc206230f82227049965b9cd3e4f49f44d5b1d27962b01eb29", "generation_seconds_batch": 20.244457046967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4989447593688965, "target_z": 1.1562501609771343, "ce": 6.2767791748046875, "genuineness": 4.061748504638672, "identity": 0.5207507610321045, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9a1603b89097de7ff1e5b3c78cb1c1ed7af8fbb1a01d505e1e84498a6debd5ef.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "9a76d517c081fb29d9bc5167702b6fa0cda37ae9946dd290dd4b6aa87f8747cc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a93aa44ca1576a6035dd4ba7075a00133e07e8bfc4f5f89fa9a3377a87e3a192", "generation_seconds_batch": 15.226053628022783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2704200744628906, "target_z": 0.9062501120726885, "ce": 6.316492557525635, "genuineness": 4.080576419830322, "identity": 0.2463599592447281, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9a76d517c081fb29d9bc5167702b6fa0cda37ae9946dd290dd4b6aa87f8747cc.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": "9b3f06e785804d2b1443e3d1f02cf7772b1abd804d157e46e1457a2e9325cb7d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Your message arrived after I had left.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa705482586179bf9774801d965d5d92b0cc31366325674a6a0ce9508949503b", "generation_seconds_batch": 15.493769360007718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0133297443389893, "target_z": 0.624999991849259, "ce": 6.395919322967529, "genuineness": 4.300237655639648, "identity": 0.35136866569519043, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9b3f06e785804d2b1443e3d1f02cf7772b1abd804d157e46e1457a2e9325cb7d.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": "9b418363910aa619e7161f4acb5e89670d0410982bcc8db8971be5f0680967e8", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The road turns left behind the bridge.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b66bc853ca1f6c7d460f2270a57f8bdf28140d01b861fd7935c78bf2d54da15d", "generation_seconds_batch": 21.697400424978696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.17401123046875, "target_z": 0.8007813495918663, "ce": 6.284721851348877, "genuineness": 4.1998209953308105, "identity": 0.4288206994533539, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I I will meet you on the other side.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9b418363910aa619e7161f4acb5e89670d0410982bcc8db8971be5f0680967e8.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "9b43bb21abb351294bd3cb7acae2692d87dde6589c5358fe352eb7cc6f7954e6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "78c89c4c4bf2d9a78be5381efca196e8c0002a9c1b4db48556c3e986bc81881c", "generation_seconds_batch": 16.353988536982797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5774998664855957, "target_z": 1.2421874006628444, "ce": 6.165581703186035, "genuineness": 4.099404335021973, "identity": 0.37252241373062134, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9b43bb21abb351294bd3cb7acae2692d87dde6589c5358fe352eb7cc6f7954e6.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": "9b7db5fbef6bf2871490e6c83a44cd45d1b2361771674f4b494def34681fe393", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The road turns left behind the bridge.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4dea4d70d81e35638b1256969024a7000050762169f384eb9f495465b4edd2be", "generation_seconds_batch": 15.524767274037004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2668492794036865, "target_z": 0.9023437553489237, "ce": 6.4912309646606445, "genuineness": 4.080576419830322, "identity": 0.355347216129303, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9b7db5fbef6bf2871490e6c83a44cd45d1b2361771674f4b494def34681fe393.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": "9bc810551673d39af84d9897399161524293e6bbabed8dd2dfb17df8ed1b88a2", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc8e72c6e2146defaf8e19476ccd874e2c110eef78b3967e34b6c74bf74d0058", "generation_seconds_batch": 16.948172027012333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.713186502456665, "target_z": 1.3906250438102328, "ce": 5.998785495758057, "genuineness": 4.457139015197754, "identity": 0.18175232410430908, "hypothesis": "De sleutels liggen op de keukentafel. Ik ik in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9bc810551673d39af84d9897399161524293e6bbabed8dd2dfb17df8ed1b88a2.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": "9be136232a49e3cd1fc01ed734e46ba84e6522c497afbfe93e18705e3e91c93c", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a35fc65a1b0d4d65b6aa43609199a40f6da86877e5afbf495f70e0fe982f9364", "generation_seconds_batch": 15.329538458958268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5132274627685547, "target_z": 1.1718750662247703, "ce": 6.38797664642334, "genuineness": 4.268857479095459, "identity": 0.41624605655670166, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9be136232a49e3cd1fc01ed734e46ba84e6522c497afbfe93e18705e3e91c93c.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "9be2f123bd4801bd455d53636cc75a85c638e4b0190c850868ab552035f489de", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7866cc1b938f092f23056d890861d544b065f339ea77580449b3ab0e8a68cd8", "generation_seconds_batch": 21.42509177303873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.663196563720703, "target_z": 1.3359373537960837, "ce": 6.086154937744141, "genuineness": 4.068024158477783, "identity": 0.3803457021713257, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9be2f123bd4801bd455d53636cc75a85c638e4b0190c850868ab552035f489de.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "9be6f0efadbad0dae56edd7c6e39ea8780bfd4c3b4258b66500207dc36014ae7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1af70609c59032209c053e9144509b3ec7a69b064dc98399d4035a989780ce69", "generation_seconds_batch": 21.08184513496235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.784600257873535, "target_z": 1.4687498308721247, "ce": 6.070269584655762, "genuineness": 3.71028995513916, "identity": 0.5298360586166382, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9be6f0efadbad0dae56edd7c6e39ea8780bfd4c3b4258b66500207dc36014ae7.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "9bec9a81673dcd220e54cfcdaff0a39de7d1931291884371b565bf8f7f40511c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "41f411527ddeaea62cc3f88b706996aad5d0a7b641271f1a60352933adf1755e", "generation_seconds_batch": 14.931687859003432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2130842208862305, "target_z": 1.937500118185744, "ce": 6.117925643920898, "genuineness": 4.143336772918701, "identity": 0.5710848569869995, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9bec9a81673dcd220e54cfcdaff0a39de7d1931291884371b565bf8f7f40511c.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "9c0930e2de2220472d009b829863f282a57f81298eaeef7a8e2c537ea09f2a5a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4277761ba51e4c81f1d2322683beb16e8f7927da712f2ddb8b9553a9d26599ab", "generation_seconds_batch": 20.135228391969576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0274078845977783, "target_z": 1.734375045847918, "ce": 6.149696350097656, "genuineness": 4.645420074462891, "identity": 0.511094331741333, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9c0930e2de2220472d009b829863f282a57f81298eaeef7a8e2c537ea09f2a5a.mp3" }, { "id": "heldout-nl-3", "language": "nl", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-3", "key": "9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Intense Interest. 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": "3eaa42916dca514a3ee486fab652583e534cae1ba4c65eed936d7f60b2f48f3b", "generation_seconds_batch": 17.890874278033152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1525869369506836, "target_z": 0.7773437308967008, "ce": 6.268836498260498, "genuineness": 4.419482707977295, "identity": 0.620308518409729, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "9c1ce9c3c8f81d6bb4d08679b4138ba4b3e2295c79588a322b5f0841b3478645", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "76b656cd1ff10f7c0a4b163bc874b65f2a12a88c2f6d4a571841bc63aab7d51e", "generation_seconds_batch": 19.30839309003204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.648913860321045, "target_z": 1.3203124485484476, "ce": 6.070269584655762, "genuineness": 3.6663577556610107, "identity": 0.535171389579773, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9c1ce9c3c8f81d6bb4d08679b4138ba4b3e2295c79588a322b5f0841b3478645.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": "9c43e12ea014c8a40429cf1cd7b9b38ed7ec00ce2956fddeadcb3b645d9a2c82", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9000c3549badf3838565239d74761e1d0876a3ed1cc542ac725358ad485c9b6f", "generation_seconds_batch": 16.969005696009845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.656055450439453, "target_z": 1.3281251619959769, "ce": 6.24500846862793, "genuineness": 4.281409740447998, "identity": 0.5213068127632141, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zum kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9c43e12ea014c8a40429cf1cd7b9b38ed7ec00ce2956fddeadcb3b645d9a2c82.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "9c505a31cebe87c5170c7d33576788962de7dd0fc0610a5f829bd117bb229d8f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4cc92045df0415be88e5bd52002210f4f44ec01f454d9be27db176f257174cb8", "generation_seconds_batch": 23.15144914900884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.891721248626709, "target_z": 1.5859374027005295, "ce": 6.292664527893066, "genuineness": 4.281409740447998, "identity": 0.6340159773826599, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9c505a31cebe87c5170c7d33576788962de7dd0fc0610a5f829bd117bb229d8f.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Intense Interest. 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": "5f9354207e22d362cfc912f4c0692c4402e71be989be9e792df2f089c28a1c6f", "generation_seconds_batch": 16.646420339937322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0204710960388184, "target_z": 0.632812444473077, "ce": 6.125868320465088, "genuineness": 4.1998209953308105, "identity": 0.5541500449180603, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "9cb47484bc8a5042cdfcca42bd6d7fafce4245c85c38264d1dcc392216153c28", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e8642da2105e0f85c59570604f9b4918b0c0481f970695eff572f17e8e8de1bd", "generation_seconds_batch": 15.048382987966761, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5844364166259766, "target_z": 2.343749741213974, "ce": 5.847874641418457, "genuineness": 4.482243061065674, "identity": 0.5266249179840088, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9cb47484bc8a5042cdfcca42bd6d7fafce4245c85c38264d1dcc392216153c28.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "9cd20577f7a4402f1afccfac896defc65929d8392bc8c8e924edb7a168f15a57", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e1833309fd3a7b53099e84f8306b064bc076553d3844d81a6dbcf2d7f2f34339", "generation_seconds_batch": 19.97549504903145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.252566337585449, "target_z": 0.8867185892775764, "ce": 6.348263263702393, "genuineness": 4.356721878051758, "identity": 0.29908549785614014, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9cd20577f7a4402f1afccfac896defc65929d8392bc8c8e924edb7a168f15a57.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "9d0c95789fe5ea41c7066f75bb886a48245972a7aa3b3b9f912d2c53fe2ac492", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "53739b17f29a0ada1d7f71a9b089dba6dd9f671f1918b460f066df47198166d0", "generation_seconds_batch": 21.28276638209354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.720327854156494, "target_z": 1.398437496434051, "ce": 6.284721851348877, "genuineness": 4.287685871124268, "identity": 0.5895519256591797, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9d0c95789fe5ea41c7066f75bb886a48245972a7aa3b3b9f912d2c53fe2ac492.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "9d2f3529cc934e03dcf01587d7795be336f33d6ff7baece1039ad383bf58713f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2c0ec33d2b4ff126e15c32cffe00e5b90420204aca0e8b316f39255fe0ceaf05", "generation_seconds_batch": 20.209604447009042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3168389797210693, "target_z": 0.9570311845393615, "ce": 6.197352409362793, "genuineness": 4.419482707977295, "identity": 0.3479998707771301, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9d2f3529cc934e03dcf01587d7795be336f33d6ff7baece1039ad383bf58713f.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "9db6caa4d683227b7a6c4c18bc64180a7a13d5e9f43f858777630ee736e69761", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "52b802db694ec5ea6f55dd36cbd17b936a4cceeec95f049122285b3f100edf17", "generation_seconds_batch": 15.331332451081835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4489548206329346, "target_z": 1.1015624709629852, "ce": 6.252951145172119, "genuineness": 4.256305694580078, "identity": 0.7183442115783691, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9db6caa4d683227b7a6c4c18bc64180a7a13d5e9f43f858777630ee736e69761.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": "9e1c88b7c8a0cac036d56bad59d0cf53758eb08654eb2576a34a0775703c36b9", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The road turns left behind the bridge.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c887759a552170940da60eca54b58856b4cfa0e64e23df95129f1e9985b4e41", "generation_seconds_batch": 21.697400424978696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.227571487426758, "target_z": 0.8593748746823575, "ce": 6.403861999511719, "genuineness": 4.1998209953308105, "identity": 0.2530995309352875, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9e1c88b7c8a0cac036d56bad59d0cf53758eb08654eb2576a34a0775703c36b9.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": "9e262453672ad7ab52d37292e5a015ad8785fa3fac1b2a34e4e2f495b3cfa3a7", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ad7619b8d12dfddbe5984ef6841bddbf0f8302bc4fc5c829a1557d11d1f008a4", "generation_seconds_batch": 20.74555579898879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.591782569885254, "target_z": 1.2578123059104804, "ce": 6.1020402908325195, "genuineness": 4.093128204345703, "identity": 0.2670266330242157, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9e262453672ad7ab52d37292e5a015ad8785fa3fac1b2a34e4e2f495b3cfa3a7.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "9ef6010eacd58944b52fdf1cb212155e10633ca0f921b210553baf782883df19", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2fabd8329abf7dc49614146ef373dd6acd98aa782895633ee3918d6b4cc37459", "generation_seconds_batch": 20.552334274048917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.527510166168213, "target_z": 1.1874999714724066, "ce": 6.149696350097656, "genuineness": 4.432034492492676, "identity": 0.2519600987434387, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9ef6010eacd58944b52fdf1cb212155e10633ca0f921b210553baf782883df19.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "9f59afbfe8b89db331c6a0fcb9097eafec4a5d266358fbc0861a9f703ee00e3a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fa8c48671e9b707e8c79321f0bd998dfab1befba969db2e1796f7754722068bc", "generation_seconds_batch": 15.463947345037013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.291844129562378, "target_z": 0.9296874699441426, "ce": 5.927301406860352, "genuineness": 4.293961524963379, "identity": 0.584312379360199, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/9f59afbfe8b89db331c6a0fcb9097eafec4a5d266358fbc0861a9f703ee00e3a.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "a03a96d82bdec816663317bc0da10445f158a6f9704df36ab0a0bdc54dc2d19e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d48e91618ef0d7d0d3500d3be55d54e900a461ddc0ffecdcd6f2e0210ce92738", "generation_seconds_batch": 17.592402137001045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.713186502456665, "target_z": 1.3906250438102328, "ce": 6.24500846862793, "genuineness": 4.337893962860107, "identity": 0.46743422746658325, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a03a96d82bdec816663317bc0da10445f158a6f9704df36ab0a0bdc54dc2d19e.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "a078c9b7a0eaea5cd3ee963574f071c13831eedfdef55eae68fb22e0aa2a40dd", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "44dc8db87c8b93189d29022b1810dc6a0b8e8fcbc4f25b729ba6a156749a2fc2", "generation_seconds_batch": 19.713481564074755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.127592086791992, "target_z": 0.7500000163014819, "ce": 6.4515180587768555, "genuineness": 4.268857479095459, "identity": 0.49873724579811096, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a078c9b7a0eaea5cd3ee963574f071c13831eedfdef55eae68fb22e0aa2a40dd.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": "a1012f58ea11b036deddcdcb352444c30e6ca42671ecfe79fe43b03163793073", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7e0620bf66ff5c500f4b291e6fb48584b6846c703a6d290e92f0771054df23e0", "generation_seconds_batch": 20.812772893928923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3204097747802734, "target_z": 0.9609375412631262, "ce": 5.442798614501953, "genuineness": 4.15588903427124, "identity": 0.42282289266586304, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a1012f58ea11b036deddcdcb352444c30e6ca42671ecfe79fe43b03163793073.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "a12cef54e8fdb3e74c80b3d9e854a0dcd0766d311056b3bad1f8a2f89135b0ad", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5cd26c1206d7a5adf7d3dad640f37a08be6741f3c275c8900239a07939db12d3", "generation_seconds_batch": 16.205260204034857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.763176202774048, "target_z": 1.4453124730006706, "ce": 6.006728172302246, "genuineness": 3.7416701316833496, "identity": 0.5401660799980164, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a12cef54e8fdb3e74c80b3d9e854a0dcd0766d311056b3bad1f8a2f89135b0ad.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "a140fb247ad5d0ecf7b3538185c5735db233de7d5710ae9e63e2c314569bdad2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5c9cf11c93617fce8f46ed6efacfa37aa6caa1083cea84bb7ecf30aa3cf4de7d", "generation_seconds_batch": 16.205260204034857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.134528636932373, "target_z": 1.8515623568526116, "ce": 6.070269584655762, "genuineness": 3.8671910762786865, "identity": 0.40691062808036804, "hypothesis": "The door is still open I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a140fb247ad5d0ecf7b3538185c5735db233de7d5710ae9e63e2c314569bdad2.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "a14bc63869457c19bfd73c51f9804f464ec9962b502d067f298e44b62b773835", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7697971096a282f73a770490c34387539a603c2235e797cb089be58f409947fb", "generation_seconds_batch": 20.27051696192939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1630945205688477, "target_z": 1.8828126889953065, "ce": 6.221180438995361, "genuineness": 4.017816066741943, "identity": 0.5827110409736633, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a14bc63869457c19bfd73c51f9804f464ec9962b502d067f298e44b62b773835.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "a17a10478af701d3cc3978d6d950bad759bb0a9510318ba124b64fd620329eac", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9c3be85ca83205ad53aef57303979312c4685bbd4f56f32d0e847d527059e45d", "generation_seconds_batch": 22.352353443042375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4989447593688965, "target_z": 1.1562501609771343, "ce": 6.205295085906982, "genuineness": 4.193545341491699, "identity": 0.40515321493148804, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a17a10478af701d3cc3978d6d950bad759bb0a9510318ba124b64fd620329eac.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "a1dd486d6249efa115d581b6626a11df45c201a01dbe2517612fa5be8315f5dc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "338b35fc83b67cf0f30a2b7fd15c5c2b9f00803bba86b8c4013938cba11813de", "generation_seconds_batch": 15.467794907046482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.998842239379883, "target_z": 1.7031249745289345, "ce": 6.1020402908325195, "genuineness": 4.570107460021973, "identity": 0.8200260400772095, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a1dd486d6249efa115d581b6626a11df45c201a01dbe2517612fa5be8315f5dc.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "a1fa0463bd1dea9b13a28d7aa7fd4d237f6e85c0dea7d6b5d8cf46312ad2aafb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5953910f77a8ab598c684d883b756ec67d9a5cbf9ff9cfa37e3b9dba290278df", "generation_seconds_batch": 21.87726035201922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3844776153564453, "target_z": 2.125000024452223, "ce": 6.205295085906982, "genuineness": 4.268857479095459, "identity": 0.5979140996932983, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a1fa0463bd1dea9b13a28d7aa7fd4d237f6e85c0dea7d6b5d8cf46312ad2aafb.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": "a26719bef3c6a86d7b8233b11e0f369481610249538c5b088d7e99b743e0ee92", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Escribí el número en el sobre.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "08d4f70cbaeb9680c042e96b664b7731515ebcee2ade0980fd4a6b8cda758ffe", "generation_seconds_batch": 16.87606308294926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.877438545227051, "target_z": 1.5703124974528935, "ce": 6.1894097328186035, "genuineness": 4.469690799713135, "identity": 0.760296642780304, "hypothesis": "Escribí el número en el sobre. Léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a26719bef3c6a86d7b8233b11e0f369481610249538c5b088d7e99b743e0ee92.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "a2a91141b7013b5cbc3b98cfaef26b681d448b60c95a96bfe0ff49d4e003028c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "040ed2e351316c7d06853fe05d9662a07cc143f5050f9decacbe254b7927a792", "generation_seconds_batch": 22.022942226030864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4418134689331055, "target_z": 1.0937500183391673, "ce": 6.2767791748046875, "genuineness": 4.469690799713135, "identity": 0.5652710795402527, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a2a91141b7013b5cbc3b98cfaef26b681d448b60c95a96bfe0ff49d4e003028c.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": "a2c97a0624e217771af76a12660eb4d3c80c910bcf2713814a22856f0d32e5fe", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ab173c7edd9ed5aafa1e32b9e41bf9e7e49024af99bc30689dbde31f6e293d9", "generation_seconds_batch": 16.992447837023064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7274692058563232, "target_z": 1.4062499490578688, "ce": 6.181467056274414, "genuineness": 4.268857479095459, "identity": 0.5787771344184875, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a2c97a0624e217771af76a12660eb4d3c80c910bcf2713814a22856f0d32e5fe.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": "a318da3dc8e50148ca7874a6f92697f00a83e75c74a48b95ce476634b7e7ede3", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b7a341c12f7b27b49766c31230a6dea79fa854200fa79e3400634862fd0c79c", "generation_seconds_batch": 17.1899752629688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.484661817550659, "target_z": 1.140624994905787, "ce": 6.205295085906982, "genuineness": 4.306513786315918, "identity": 0.6621790528297424, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a318da3dc8e50148ca7874a6f92697f00a83e75c74a48b95ce476634b7e7ede3.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "a355460b46cd599ef8c2759d7fe8d68f253ee73f1d3b496f1a9ae064bbe3b5c1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7ded281b3fa827e5b3713a2e0fb54a87448f119c0fa34ba477118f3c88b556c5", "generation_seconds_batch": 21.586594316991977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5774998664855957, "target_z": 1.2421874006628444, "ce": 6.117925643920898, "genuineness": 4.482243061065674, "identity": 0.6353031992912292, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a355460b46cd599ef8c2759d7fe8d68f253ee73f1d3b496f1a9ae064bbe3b5c1.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "a3b8cb7c9b016f1f83ed3e902de0f5444aa82f37037c7a26faa0352a727af60a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46edc49f2c230f615c8e2532deb0bc3ac22575c5e9cfeb4af7f7d55823ba5281", "generation_seconds_batch": 14.689185076043941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6203484535217285, "target_z": 1.2890626380531753, "ce": 6.117925643920898, "genuineness": 3.8671910762786865, "identity": 0.515513002872467, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a3b8cb7c9b016f1f83ed3e902de0f5444aa82f37037c7a26faa0352a727af60a.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": "a4650f6722704bf0eeb97c9cd8afe78c93aa0f022b8910fdc53dc58f22581699", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de2236aa9dcef9c4d76bf1019bb9aa27162ea5afd47705a693d26e21eaa2ed24", "generation_seconds_batch": 20.68235179304611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.827448844909668, "target_z": 1.5156250682624557, "ce": 6.252951145172119, "genuineness": 4.595211505889893, "identity": 0.6437267065048218, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les. Quand tu partiras ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a4650f6722704bf0eeb97c9cd8afe78c93aa0f022b8910fdc53dc58f22581699.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "a46b34840c0feb44c82b2ce65d27e41143218d1034f98100554524713038c819", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "aa8757e2312fb17c3bd3ce83d4a12a5c7907282f66ee9cabd39055b442db30fd", "generation_seconds_batch": 20.328406741959043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9704813957214355, "target_z": 0.5781250152826394, "ce": 6.1894097328186035, "genuineness": 4.017816066741943, "identity": 0.24000394344329834, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a46b34840c0feb44c82b2ce65d27e41143218d1034f98100554524713038c819.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "a4ed278e1d8a4cbc41ab22645c334170e0024a25743adcb4615048fc7b57ba2a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7efe72504a32dd47dbcc2784de23a59005f2deea010c179c6b279a3112bb7b09", "generation_seconds_batch": 23.713490245048888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.94191575050354, "target_z": 0.5468749439636558, "ce": 5.903473377227783, "genuineness": 4.049196243286133, "identity": 0.39677515625953674, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a4ed278e1d8a4cbc41ab22645c334170e0024a25743adcb4615048fc7b57ba2a.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "a52ef9fe405e218f0fbe0bc1d505a941b84b19a439172f0e79387cafdf318f2b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "feb07fcd17cac2588f7936979b44ba242cda50d6c0576b087d34654809d5069a", "generation_seconds_batch": 22.420462378067896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.35591197013855, "target_z": 2.0937499531332393, "ce": 6.0146708488464355, "genuineness": 4.024092197418213, "identity": 0.42276567220687866, "hypothesis": "I found the little box! It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a52ef9fe405e218f0fbe0bc1d505a941b84b19a439172f0e79387cafdf318f2b.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": "a53efd189d7385a1c89e623db7d2bd364d4d4d01a9b843916137199570c52284", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a73e4ce45ca03f3041fecec7cee60c75cef60eb6ff9f82a366e0135e863608c", "generation_seconds_batch": 16.256331390002742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8131661415100098, "target_z": 1.5000001630148196, "ce": 6.316492557525635, "genuineness": 4.20609712600708, "identity": 0.6766003370285034, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a53efd189d7385a1c89e623db7d2bd364d4d4d01a9b843916137199570c52284.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "a55078d595c3c87deea467e12185169d400c844843d75a578d9fe884f90a7ad3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "677add44aeecfe57b78a4b9119905a26fcd75ea3575ea8f079ef39c6925d5c83", "generation_seconds_batch": 25.02811310708057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9774179458618164, "target_z": 1.679687355833769, "ce": 6.117925643920898, "genuineness": 3.7667744159698486, "identity": 0.09639802575111389, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a55078d595c3c87deea467e12185169d400c844843d75a578d9fe884f90a7ad3.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "a5552bc2da501a5a388835567db71dad2b6f4a4861db0c1d6ea2a1ce796817cd", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7065531783430f1f308d99a1f9580dd68abf906088e4ce0295b66905a07f0c46", "generation_seconds_batch": 21.80314856301993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.120245933532715, "target_z": 1.8359374516049753, "ce": 5.673136234283447, "genuineness": 3.9927117824554443, "identity": 0.3353719115257263, "hypothesis": "¡La puerta sigue abierta! He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a5552bc2da501a5a388835567db71dad2b6f4a4861db0c1d6ea2a1ce796817cd.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "a56725736eaa2131d4452bc1cbe10a739d42c663780e23241a325eee74d9aa58", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cdb1c1a43cab788e0507ff3fcba628da589d6bd1e5df8ba04fb801f0904a1f2e", "generation_seconds_batch": 21.882110688020475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.995476245880127, "target_z": 0.6054687298778582, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.7971147894859314, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a56725736eaa2131d4452bc1cbe10a739d42c663780e23241a325eee74d9aa58.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "a5d7a298a32929d1c489dd801a6f2d2abda26af39d9816c692ad2b029981b950", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5bf8b7e991389d6e016ce62c2e21e9262099019373d57025ec159f24c1c90511", "generation_seconds_batch": 23.09919051604811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3846821784973145, "target_z": 1.0312498757012, "ce": 6.0305562019348145, "genuineness": 4.20609712600708, "identity": 0.2517385482788086, "hypothesis": "Gitühr ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist!", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a5d7a298a32929d1c489dd801a6f2d2abda26af39d9816c692ad2b029981b950.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "a6a5741bdcfc92fdb601bc2a98e1f6883ad61bb1fb630b28d8071bfd54b86706", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "501b4b3d482451de92010234e568e998592f997dd20b820d43d1a04ec6408406", "generation_seconds_batch": 15.21351994399447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3132684230804443, "target_z": 0.9531250886393081, "ce": 6.316492557525635, "genuineness": 4.457139015197754, "identity": 0.56879723072052, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a6a5741bdcfc92fdb601bc2a98e1f6883ad61bb1fb630b28d8071bfd54b86706.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": "a73821e66a26208fc04f84170f2f3f3825b4d1d43e9a7f8d20623baa279a9c1b", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "338aa48281425303bd2cf33e85f9d1565680962d3232d621bf0fea9975e793f4", "generation_seconds_batch": 15.268667532945983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4560961723327637, "target_z": 1.1093749235868033, "ce": 6.316492557525635, "genuineness": 4.607763767242432, "identity": 0.5636119246482849, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a73821e66a26208fc04f84170f2f3f3825b4d1d43e9a7f8d20623baa279a9c1b.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "a767b9d03ea5a1f72ee97190a1161dd2c933f4d344ed4e1a6aa70ef2ebb651aa", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c66f17f7c626d9b9a5073739b8a6415b87a874ea2e223adfb13c520450bcd9c", "generation_seconds_batch": 20.99159629002679, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3273463249206543, "target_z": 2.0624998818142557, "ce": 5.557967185974121, "genuineness": 3.9676074981689453, "identity": 0.34863924980163574, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a767b9d03ea5a1f72ee97190a1161dd2c933f4d344ed4e1a6aa70ef2ebb651aa.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "a7c0302eb75dca221fc421bf1d69bfe677f03e2af0fae72ea8dd208a535d0a34", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f7e5c8ceb4a161a41d1fd829a5c3ea4abc73d5c4d8f0dc5e8ea47d38d2cf91b3", "generation_seconds_batch": 22.260196185903624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4130430221557617, "target_z": 2.156249834947495, "ce": 6.24500846862793, "genuineness": 4.287685871124268, "identity": 0.4353495240211487, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a7c0302eb75dca221fc421bf1d69bfe677f03e2af0fae72ea8dd208a535d0a34.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "a7e7927d423f454aefda8ecd8565f6467dce6a81849ff810fe66f81fcc941cae", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a259bd6f70cd312d39e6881a65070d75fb13376bdba2c8498e1614fd8f4de734", "generation_seconds_batch": 20.689047247054987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0988216400146484, "target_z": 1.8124998329098099, "ce": 5.216432571411133, "genuineness": 3.823258876800537, "identity": 0.4667224884033203, "hypothesis": "¡La puerta sigue abierta! He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a7e7927d423f454aefda8ecd8565f6467dce6a81849ff810fe66f81fcc941cae.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "a8346d33525cb1321f083803907beed199b40ae7e8f5439fbc10cf8776977099", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f69bbf86b3e48e6503dd98e9668db58af70902fd0069e7bee9ce92d51d982651", "generation_seconds_batch": 19.30561691906769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4560961723327637, "target_z": 1.1093749235868033, "ce": 6.173524379730225, "genuineness": 4.080576419830322, "identity": 0.1767456829547882, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a8346d33525cb1321f083803907beed199b40ae7e8f5439fbc10cf8776977099.mp3" }, { "id": "heldout-nl-4", "language": "nl", "sentences": [ "Ik schreef het nummer op de envelop.", "Lees het goed... en controleer de laatste twee cijfers.", "Bel me wanneer je even tijd hebt." ], "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-4", "key": "a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Intense Interest. 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": "5f47444998a14900e1f44ad1da088d4af4080c7150576628a8b935311416a9b0", "generation_seconds_batch": 17.793920486001298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3703994750976562, "target_z": 1.015624970453564, "ce": 6.09409761428833, "genuineness": 4.218649387359619, "identity": 0.7098211050033569, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "a8ee706e8ee83f68def7b4685ac03f35a599ce74bda12c7fce8682bdcd3721dc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8cf59096387074ddb3c3dfbef61229a104523241efbc98f2f700675761760c23", "generation_seconds_batch": 20.64773129997775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6346311569213867, "target_z": 1.3046875433008114, "ce": 5.33954381942749, "genuineness": 3.5816311836242676, "identity": 0.5552412867546082, "hypothesis": "The door is still open! I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a8ee706e8ee83f68def7b4685ac03f35a599ce74bda12c7fce8682bdcd3721dc.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Intense Interest. 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": "24e03ac7cec4d3d70407b89fe68dfd6adaa9233fd4c71758e997d827afe9a1b8", "generation_seconds_batch": 16.94332864799071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.999047040939331, "target_z": 0.6093750866016229, "ce": 6.165581703186035, "genuineness": 4.331617832183838, "identity": 0.6685342192649841, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "a9ccc9077aa6e7f66aa9101134705f3729933847aa421be34d523a3138e31ff6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9e5556b64473d0d100026dcfb6ed237598d835a5f0e8c75c37818d5d673d397d", "generation_seconds_batch": 20.7474313180428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.116879940032959, "target_z": 0.7382812069538992, "ce": 6.41180419921875, "genuineness": 4.15588903427124, "identity": 0.3297252357006073, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/a9ccc9077aa6e7f66aa9101134705f3729933847aa421be34d523a3138e31ff6.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "aa03b62ba45d7c5ba107a30434815eaaea3224debb7fe82cc60f3ed4c18308eb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9edd6e4bbf0978e0d18ee9832f1ba0ef955a643e26830f35f4c2c755e708a3ca", "generation_seconds_batch": 20.93570679507684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.227571487426758, "target_z": 0.8593748746823575, "ce": 6.229123115539551, "genuineness": 4.369274139404297, "identity": 0.7405638098716736, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/aa03b62ba45d7c5ba107a30434815eaaea3224debb7fe82cc60f3ed4c18308eb.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": "aa05d753a13e114244617a15d700c035333a1d5c2b152d401ed6965a4ab70425", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d092ddd463980bd46c81eb4f520e74b3a6a05b316e82c35a5645b6ea9490b7cd", "generation_seconds_batch": 15.465024960925803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8131661415100098, "target_z": 1.5000001630148196, "ce": 6.054384231567383, "genuineness": 4.243753433227539, "identity": 0.6602453589439392, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/aa05d753a13e114244617a15d700c035333a1d5c2b152d401ed6965a4ab70425.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "aac4273ac2801c85975c34254f6a8ad0cc6dcba5b3fbc1d1401a564419ff6a01", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "dbc6f57c3fd1d13b221d23f3cc6d3a787d1317df09077986b294e54ee35a1c80", "generation_seconds_batch": 16.54666788794566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.063114643096924, "target_z": 1.7734373089670084, "ce": 6.292664527893066, "genuineness": 4.293961524963379, "identity": 0.47085124254226685, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/aac4273ac2801c85975c34254f6a8ad0cc6dcba5b3fbc1d1401a564419ff6a01.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "ab043597d5d38feaba8d64ed3d8f9ee7c6052576e89bc4d4de20ff9ecd27bd34", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2fb5b3199de03012501d16bd4b66353df6e6e131b58b8a96084bdc7d41276da1", "generation_seconds_batch": 20.670913356007077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6203484535217285, "target_z": 1.2890626380531753, "ce": 6.205295085906982, "genuineness": 4.268857479095459, "identity": 0.6749731302261353, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ab043597d5d38feaba8d64ed3d8f9ee7c6052576e89bc4d4de20ff9ecd27bd34.mp3" }, { "id": "heldout-en-0", "language": "en", "sentences": [ "Your message arrived after I had left.", "I read it twice... before putting the phone away.", "Let me know when we can talk." ], "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-0", "key": "ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9da99e2a99138762d597bae12e7dd7f4d3a32236b26c1616cb5c967f507957e5", "generation_seconds_batch": 16.896964655956253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.668757438659668, "target_z": 0.24804687054256352, "ce": 6.459460258483887, "genuineness": 4.306513786315918, "identity": 0.4403954744338989, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "abeb1a8b5fc8f391fe0ed29c2cf0068b0d58fc21d470d44be0c883bbe4f6949c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a4730e3cd08eaeec906bee2e618dc96d2baff2a361faf4cce822ede10dcc445c", "generation_seconds_batch": 16.122312884079292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9202868938446045, "target_z": 1.6171874740195131, "ce": 6.395919322967529, "genuineness": 4.174716949462891, "identity": 0.3910452425479889, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/abeb1a8b5fc8f391fe0ed29c2cf0068b0d58fc21d470d44be0c883bbe4f6949c.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "ad60efb3a91d16fd530de804913fdd37ae94d799b99de951faac12fb4ec36bd7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "98fcf5732ff81643862a062a09a19998ce8db003b53e4e40688840b15d4f035e", "generation_seconds_batch": 20.19185280392412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8203072547912598, "target_z": 1.5078123548149263, "ce": 5.95112943649292, "genuineness": 3.948779582977295, "identity": 0.11797618865966797, "hypothesis": "De deur staat nog open! Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ad60efb3a91d16fd530de804913fdd37ae94d799b99de951faac12fb4ec36bd7.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "ad791e811db20916e2e29ad9c34e5165a37812a05be9fbbbe89b916e2e4b8d58", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c4bc83051f56730ea451a16284dc98a8aedb77ceb9116e191f72ed6f8b8ec659", "generation_seconds_batch": 19.777131546055898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.763176202774048, "target_z": 1.4453124730006706, "ce": 6.157639026641846, "genuineness": 4.545003414154053, "identity": 0.5793828368186951, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ad791e811db20916e2e29ad9c34e5165a37812a05be9fbbbe89b916e2e4b8d58.mp3" }, { "id": "heldout-nl-0", "language": "nl", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-0", "key": "adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Intense Interest. 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": "8cd51c74c0fe5dfe291712ccd3fb3d3f549c8e94d1206d16d2a3f5e6e5111011", "generation_seconds_batch": 15.881895263912156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1418747901916504, "target_z": 0.7656249215491181, "ce": 6.229123115539551, "genuineness": 4.344170093536377, "identity": 0.34276866912841797, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.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": "add97a5b44b2df68d67401cd9f17cf0ce8d7e59a2cb42e37df38f9e698c4cfaf", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45a3a5389983bf0b35b8e5c866837f7aad25c1bcd3c225b56299757a4bcd9e60", "generation_seconds_batch": 14.73156733601354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9202868938446045, "target_z": 1.6171874740195131, "ce": 6.149696350097656, "genuineness": 4.030367851257324, "identity": 0.36708372831344604, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/add97a5b44b2df68d67401cd9f17cf0ce8d7e59a2cb42e37df38f9e698c4cfaf.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": "ade8c60d525219e0cb78ee9c691808be298de465bd095e5d45a7ed3fdc5e0ce3", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8339e1a785e746374ca3555844770d42d03f47550d4022dc4d8658618c184e26", "generation_seconds_batch": 15.350442867027596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6917624473571777, "target_z": 1.3671876859387786, "ce": 6.23706579208374, "genuineness": 4.319066047668457, "identity": 0.39587777853012085, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ade8c60d525219e0cb78ee9c691808be298de465bd095e5d45a7ed3fdc5e0ce3.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "adea2820da40b99402bbad439c7dc8c751cdf606c9638dbfeb9631209b4054bb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "465c7cb34ae34a2ef5789070d61425e840b3f70cd540fd226a38b3b32ffddf8a", "generation_seconds_batch": 15.121650255983695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.470378875732422, "target_z": 1.1249998288344394, "ce": 6.157639026641846, "genuineness": 4.319066047668457, "identity": 0.7237883806228638, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/adea2820da40b99402bbad439c7dc8c751cdf606c9638dbfeb9631209b4054bb.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "ae28822f26034ad2cc989f736fb9df52399d880cea83ad1db03a30d84d4c14ad", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b41b4dcd4c8e945d4e0cfe6c0134f1cf9e5723e1392c77d59dd0765cdb43f646", "generation_seconds_batch": 20.18271615996491, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.063114643096924, "target_z": 1.7734373089670084, "ce": 5.990842819213867, "genuineness": 3.8169827461242676, "identity": 0.40728092193603516, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ae28822f26034ad2cc989f736fb9df52399d880cea83ad1db03a30d84d4c14ad.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Intense Interest. 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": "08ae1efd60f1ca5294eb4942ebf19a70f6c260fb24270fdb8b1cd4873fcc43a0", "generation_seconds_batch": 16.25422698399052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9883348941802979, "target_z": 0.5976562772540401, "ce": 6.459460258483887, "genuineness": 4.432034492492676, "identity": 0.36799731850624084, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.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": "aec51bf3db65380aa3c1ea4a5054dec4f4aec5eb28810d45aef52eb63bd35248", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ab35535a70d216f4ad1cc8d7f1fc0602581c1e293e24a1f7fddaba55f0e45ba6", "generation_seconds_batch": 15.273313436075114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1490163803100586, "target_z": 0.7734376349966474, "ce": 6.197352409362793, "genuineness": 4.570107460021973, "identity": 0.7081102132797241, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/aec51bf3db65380aa3c1ea4a5054dec4f4aec5eb28810d45aef52eb63bd35248.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "aee88c7dee5c2d82c06ef4cccbed5ff2f3bb5586da542acc8c779908abe09ec2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e0b9e1fe4758c46c2785da4b4a229a872051f1375799c774ed0a32fa59b96c81", "generation_seconds_batch": 16.76758820109535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0383245944976807, "target_z": 0.6523437064444779, "ce": 6.141753673553467, "genuineness": 4.18726921081543, "identity": 0.4062272310256958, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/aee88c7dee5c2d82c06ef4cccbed5ff2f3bb5586da542acc8c779908abe09ec2.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "af3ceeb3b02130a46f3158680665ce6dcab2d1c51da18422d91ee2828b03f088", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5121098782605ee50b7aeb0811f66756b315599a5e2720181a53f916c27fc528", "generation_seconds_batch": 23.362886833958328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.541792869567871, "target_z": 1.2031248767200426, "ce": 6.125868320465088, "genuineness": 3.998987913131714, "identity": -0.024070128798484802, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/af3ceeb3b02130a46f3158680665ce6dcab2d1c51da18422d91ee2828b03f088.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "af7ea9c1fbba097c7a16ae77a6a5f3b0a3030c2b9efde3501b0a96e69928c869", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "22c984c35016e2eb813128f41109943b38b9780a70b36f064a9daeb3cdce39d3", "generation_seconds_batch": 21.42509177303873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3096976280212402, "target_z": 0.9492187319155434, "ce": 6.022613525390625, "genuineness": 3.873466968536377, "identity": 0.019498419016599655, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/af7ea9c1fbba097c7a16ae77a6a5f3b0a3030c2b9efde3501b0a96e69928c869.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "afa118bf6bf3da56d161d865c541d36ca97e323a8f4a49ba36c260644deb432c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "50fde05092f56a3381ff7ca118bf9c343de00b10d1522d16f73f6da85e9f290c", "generation_seconds_batch": 22.352353443042375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0418953895568848, "target_z": 0.6562500631682425, "ce": 6.0146708488464355, "genuineness": 4.507347106933594, "identity": 0.5709642171859741, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/afa118bf6bf3da56d161d865c541d36ca97e323a8f4a49ba36c260644deb432c.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "afaa6631ebdce82649a549f56c3afe77f6761b5394ad819796888e948b32b0d6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "77aa4ee9a7b0018308498f25da014d937ba0c306ba730132e79bb4cfa2f7b268", "generation_seconds_batch": 23.01652722398285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9276330471038818, "target_z": 0.5312500387160196, "ce": 5.879645347595215, "genuineness": 4.268857479095459, "identity": 0.4286908507347107, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/afaa6631ebdce82649a549f56c3afe77f6761b5394ad819796888e948b32b0d6.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": "afb20679da5334456a793d9f2236bd748352c967cdbe4bbf91e81139e1193e04", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Escribí el número en el sobre.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1077532caf44007167e1d44bc0a57d0cafcfda8a7ff8e040c524b80e6a7a9749", "generation_seconds_batch": 14.862233455991372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8060245513916016, "target_z": 1.4921874495672902, "ce": 6.0146708488464355, "genuineness": 3.9299514293670654, "identity": 0.6141184568405151, "hypothesis": "Escribí el número en el sobre, léelo bien, y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/afb20679da5334456a793d9f2236bd748352c967cdbe4bbf91e81139e1193e04.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "afc8f731f02fbd2222f3c58b2deb81c613b43ea6687778698339ef9ea9df072b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "992b2572118ccdbb4b8714cb9df0d6156284e070fb6d379d9a1d941f16d7831c", "generation_seconds_batch": 22.293617054936476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245425224304199, "target_z": 0.8789063974774696, "ce": 6.197352409362793, "genuineness": 4.545003414154053, "identity": 0.6275849938392639, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/afc8f731f02fbd2222f3c58b2deb81c613b43ea6687778698339ef9ea9df072b.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "b02b6ea406c5cd38fe84d1f79b3d4c412acda5a8ae14914c7093cb7ba3399253", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "497037630ff773891fb1840850b363a9099afca362716b6d1878285ddcb457ee", "generation_seconds_batch": 23.581020860001445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0418953895568848, "target_z": 0.6562500631682425, "ce": 6.109982967376709, "genuineness": 4.243753433227539, "identity": 0.7173012495040894, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b02b6ea406c5cd38fe84d1f79b3d4c412acda5a8ae14914c7093cb7ba3399253.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "b0319a0a7b64ea06ec403774232fadc7e988a5bda33c6280047ac36ced2a5cbe", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "73b0f882f3d4adc54db20281dfa351be4996a344f3a5902b975660fbe1d0e8b7", "generation_seconds_batch": 15.143071830039844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3168389797210693, "target_z": 0.9570311845393615, "ce": 5.696964263916016, "genuineness": 3.936227321624756, "identity": 0.4313381314277649, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b0319a0a7b64ea06ec403774232fadc7e988a5bda33c6280047ac36ced2a5cbe.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": "b044a10f120cdd97eb1d12ba8e58ef2ed5d471deac612a4bd77a40f28ab9dc43", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Your message arrived after I had left.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6a8b0479f197345f35a16c9ba9bea220cebf2110d7bbc8da7877d9a55a07c46d", "generation_seconds_batch": 15.493769360007718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1490163803100586, "target_z": 0.7734376349966474, "ce": 6.356205940246582, "genuineness": 4.231201171875, "identity": 0.30777159333229065, "hypothesis": "Your message arrived after I had left. I read it twice. Before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b044a10f120cdd97eb1d12ba8e58ef2ed5d471deac612a4bd77a40f28ab9dc43.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "b0925197e299a07bf505a9dea69749fccaa28f5fe05f0891f9df4cc2bd7006f6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7b9e971b5eca3c9eefd0633adaa0486a349116d9303a0a96712f25dafa50cf4f", "generation_seconds_batch": 21.258628226001747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.345404624938965, "target_z": 0.988281255858345, "ce": 6.252951145172119, "genuineness": 4.444586753845215, "identity": 0.7055178880691528, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b0925197e299a07bf505a9dea69749fccaa28f5fe05f0891f9df4cc2bd7006f6.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "b0ac510d3b9562f42f62965e4b184ecae0cbd78d42bd0da1b823a9d23552c249", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "67752f1c979d5aa397cfe44a0f51e96bdf338233883070ef71277bffa5287d01", "generation_seconds_batch": 16.088412580895238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 6.419747352600098, "genuineness": 4.168440818786621, "identity": 0.4340474605560303, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b0ac510d3b9562f42f62965e4b184ecae0cbd78d42bd0da1b823a9d23552c249.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "b0c6c472a56f28677ee16042f650644ea550bfb42944de63d4262afd1d825559", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "20429f6aa1248dc232de9fb9b4783cddc68124e1839d436850dbc7b18401c2a2", "generation_seconds_batch": 21.00411892007105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4989447593688965, "target_z": 1.1562501609771343, "ce": 6.117925643920898, "genuineness": 4.394378662109375, "identity": 0.5864983797073364, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b0c6c472a56f28677ee16042f650644ea550bfb42944de63d4262afd1d825559.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "b10f271a9c17e0732ad704e30b91c95ab28ce6ff2100b0917859898e0a400813", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b07e7e50c8f9c7466723054c320097b3eafdb5e37c5f9ef088e0ffb9ae3566a3", "generation_seconds_batch": 23.302493105991744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.059748888015747, "target_z": 0.6757813251396434, "ce": 6.252951145172119, "genuineness": 4.344170093536377, "identity": 0.6446532011032104, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b10f271a9c17e0732ad704e30b91c95ab28ce6ff2100b0917859898e0a400813.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "b11a84ec89792ef6668e036bb64965b00e578ce6a4f5300ae8d7b39ea69c1c38", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f412e180ac20eda692a620062ed5a8be4f8ee6bfaa928561e704aa390cc8f255", "generation_seconds_batch": 15.31947924697306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.313063621520996, "target_z": 2.04687497656662, "ce": 6.300607204437256, "genuineness": 4.18726921081543, "identity": 0.31393080949783325, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b11a84ec89792ef6668e036bb64965b00e578ce6a4f5300ae8d7b39ea69c1c38.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "b1d3d92324b6b58e5c9b8f29b79f42711fb30e1452bc8a6f113fc790694b072e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "83a8cb8b571fb6b13e69ce616d342432cde71391beb6cb7fc784fd6f33d698de", "generation_seconds_batch": 17.599005733965896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.55587100982666, "target_z": 2.3124999307187015, "ce": 5.665193557739258, "genuineness": 4.137060642242432, "identity": 0.5436856150627136, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b1d3d92324b6b58e5c9b8f29b79f42711fb30e1452bc8a6f113fc790694b072e.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "b1d4f70618f0742e883c9d5d597c3735872a42e91042537907e5b6d15eefbc55", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "21729cff4c1d243f695ede335edf00e7414dff3b3a816404eabd6925c719b160", "generation_seconds_batch": 19.30561691906769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.777459144592285, "target_z": 1.460937639072018, "ce": 6.221180438995361, "genuineness": 4.13078498840332, "identity": 0.33940982818603516, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b1d4f70618f0742e883c9d5d597c3735872a42e91042537907e5b6d15eefbc55.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "b1d54a9bf1ddde14220ddb8f39b8bfec12c0e7e0fd5f4292a94d07267dfc21fa", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f20908b71f899b875bd47cbecbcf22a237f158845e315f0bab56e1fc44e47cac", "generation_seconds_batch": 19.936314187943935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.268836498260498, "genuineness": 4.419482707977295, "identity": 0.41582632064819336, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b1d54a9bf1ddde14220ddb8f39b8bfec12c0e7e0fd5f4292a94d07267dfc21fa.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": "b1e7f461b09828cfcb3e97e97326a612326631b0215ccc913f6490d9607fe0a0", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b91b9b35ea47793cd8c1f97cc80d771e127b784e48932dc74a6dceaf4e930a0f", "generation_seconds_batch": 20.63684871303849, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2561371326446533, "target_z": 0.890624946001341, "ce": 6.213237762451172, "genuineness": 4.118232727050781, "identity": 0.48374685645103455, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b1e7f461b09828cfcb3e97e97326a612326631b0215ccc913f6490d9607fe0a0.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "b22df508517cea344642af8a9f93c757394ca4caa06cfbe7be5ce15e2fd3e8e4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2f862adf513363a471e0ee8312db2aea397a04734a9f07854539fe85f2542c54", "generation_seconds_batch": 21.006562340073287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2844982147216797, "target_z": 2.0156251660713473, "ce": 5.816103935241699, "genuineness": 4.099404335021973, "identity": 0.4280157685279846, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b22df508517cea344642af8a9f93c757394ca4caa06cfbe7be5ce15e2fd3e8e4.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "b23bba2ca1ee897f3959db3962ecdd335c60ee34b19bcc68d997afb17114c138", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "19a8b82cb3a169cdd84798d74ea6b85fac3c2937c4b1ee9b073ea9e7781495e5", "generation_seconds_batch": 15.25920651294291, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.420389175415039, "target_z": 1.0703123996440018, "ce": 6.2767791748046875, "genuineness": 4.632867813110352, "identity": 0.6653308868408203, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b23bba2ca1ee897f3959db3962ecdd335c60ee34b19bcc68d997afb17114c138.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "b293b03cf9b00637efc13836a04bcb17389ecf5c3fe4c4bb7f0ec3d011682209", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1963d9f2156f447e8cc2306486f1e26ca692303f7dabddb9345cccf6dc5e9d0e", "generation_seconds_batch": 20.071417708997615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4416089057922363, "target_z": 2.18750016709019, "ce": 6.229123115539551, "genuineness": 4.174716949462891, "identity": 0.5053991079330444, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b293b03cf9b00637efc13836a04bcb17389ecf5c3fe4c4bb7f0ec3d011682209.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "b312498e0660f0f3b4ce6f7ee5625bed30e3ff244ecc17b5be5dc9fc7bb5e2a9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d62a480aff71514a396e7b0dc69d736e8eefecbb98f6273b303376eccaaeb8ee", "generation_seconds_batch": 26.489686407032423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9917008876800537, "target_z": 1.6953125219051164, "ce": 6.149696350097656, "genuineness": 4.344170093536377, "identity": 0.598139762878418, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b312498e0660f0f3b4ce6f7ee5625bed30e3ff244ecc17b5be5dc9fc7bb5e2a9.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "b32b38e52dd6fda32b54582efcee490989b2f5abac137d73c9157e87823d4a61", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b35f4a33145a9411c58690b69e60915f296e328a2f34aa1b062dc8ea59b2622a", "generation_seconds_batch": 15.048382987966761, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5844364166259766, "target_z": 2.343749741213974, "ce": 5.824047088623047, "genuineness": 4.105680465698242, "identity": 0.5246989727020264, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b32b38e52dd6fda32b54582efcee490989b2f5abac137d73c9157e87823d4a61.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "b34e2f92c142d1dfa7f5fe4d2d37b57a3f17398da3f0d65055d7df0e195853e8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "70956f6043d2cdd1accdd42fa242b6acd16d2f881832f613132791f1b7818eff", "generation_seconds_batch": 20.63430152204819, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0918850898742676, "target_z": 0.7109374923586803, "ce": 5.998785495758057, "genuineness": 4.306513786315918, "identity": 0.5868906378746033, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b34e2f92c142d1dfa7f5fe4d2d37b57a3f17398da3f0d65055d7df0e195853e8.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": "b3db85b837d5bda867b184e02fed0f9fdbf778117409be4f9af63167f017b39f", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4838e50b15b1d91d40058b49e22fc2a699be263b3615e7cea7beccd616e8df50", "generation_seconds_batch": 16.992447837023064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.598924160003662, "target_z": 1.2656250193580099, "ce": 6.006728172302246, "genuineness": 4.243753433227539, "identity": 0.41353654861450195, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b3db85b837d5bda867b184e02fed0f9fdbf778117409be4f9af63167f017b39f.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "b3e4b751a3fc7b020348c5bbdfd83dffa00ceb7b9d415145b75b96e8d09e184f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2094eb9f3064e36ac0c53eb3d4df787c92e2ce6c9344b4639a8150d50db6d559", "generation_seconds_batch": 21.6509872530587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.420389175415039, "target_z": 1.0703123996440018, "ce": 6.006728172302246, "genuineness": 3.8797430992126465, "identity": 0.38455843925476074, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b3e4b751a3fc7b020348c5bbdfd83dffa00ceb7b9d415145b75b96e8d09e184f.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Intense Interest. 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": "4a2aaf2290381394e2da3c86f251c81608b8c34932009fea7939d6568dfd1d07", "generation_seconds_batch": 15.53630890196655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 6.38797664642334, "genuineness": 4.293961524963379, "identity": 0.47121602296829224, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "b433558a8cdf13efd62fde14853483d2ff5fad23801f0aaf156eea86f630eed4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "deffe7e26bcf3b00dcead3de86770e5fe88243b39b4cb219d95531fb2d816141", "generation_seconds_batch": 22.551954924943857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.541792869567871, "target_z": 1.2031248767200426, "ce": 6.0146708488464355, "genuineness": 4.024092197418213, "identity": 0.42440974712371826, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b433558a8cdf13efd62fde14853483d2ff5fad23801f0aaf156eea86f630eed4.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": "b43b09f5aae109f115ae8f042e160fe1299ba937bdeec3852f302adea17c5d21", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The road turns left behind the bridge.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "98bed98f440adece38518a97e7a159731b307c042534e640606180af76131dfb", "generation_seconds_batch": 15.769169289036654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1347334384918213, "target_z": 0.7578124689253001, "ce": 6.308549880981445, "genuineness": 3.9299514293670654, "identity": 0.5331678986549377, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b43b09f5aae109f115ae8f042e160fe1299ba937bdeec3852f302adea17c5d21.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "b4cd8f32e80e3d595ba9059dd30013a9efc88c55fc616d331c16843237204ca4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ca8f4c9f6c076a42489f9e2089e8eabe9644a2cff418c48a9a723243700ea0f8", "generation_seconds_batch": 15.900884718052112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.484457015991211, "target_z": 2.2343748828330985, "ce": 6.173524379730225, "genuineness": 4.055472373962402, "identity": 0.6602752208709717, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b4cd8f32e80e3d595ba9059dd30013a9efc88c55fc616d331c16843237204ca4.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "b4f264f42167323b547447e621bcf8499ca76d7b20685d2875aba6705eb7e0a3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6d23a5ab664999c9939ee08935ec69d62c983c53db1dab743e3c828b975bee9a", "generation_seconds_batch": 21.910660989000462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.541588306427002, "target_z": 2.2968750254710657, "ce": 5.665193557739258, "genuineness": 4.137060642242432, "identity": 0.3756522536277771, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b4f264f42167323b547447e621bcf8499ca76d7b20685d2875aba6705eb7e0a3.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "b52ae914fcec21652604f1ad28860786a60d3a0af1416d9568556db33c806f93", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "880119e6b1b8ff0aee7f8a5122726bad4ca4f950f12c71feca52e2f6fc0ecb6c", "generation_seconds_batch": 22.34117997100111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5844364166259766, "target_z": 2.343749741213974, "ce": 6.117925643920898, "genuineness": 4.218649387359619, "identity": 0.507564902305603, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b52ae914fcec21652604f1ad28860786a60d3a0af1416d9568556db33c806f93.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "b605c50a52351fd45cfffe3e566a64af57845edbc241c68c2844b121ad0955d0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "baf304a7e0695e4727967e9e0b4a3ad32d9277ba86bbe9925bdfd60001454428", "generation_seconds_batch": 23.12743502401281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.420389175415039, "target_z": 1.0703123996440018, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.5279420614242554, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b605c50a52351fd45cfffe3e566a64af57845edbc241c68c2844b121ad0955d0.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "b63b7db23827e22efdbdd4c1f513137afb56ca84165bd40147c637a72fb6613a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a29d4e86220e711176f5caab9e897b4eee97af83928fa0cb0571a9fd41fe741a", "generation_seconds_batch": 15.317588392994367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1702356338500977, "target_z": 1.8906248807954131, "ce": 5.6254801750183105, "genuineness": 3.986435890197754, "identity": 0.3147084712982178, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b63b7db23827e22efdbdd4c1f513137afb56ca84165bd40147c637a72fb6613a.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "b76a0eb241df56c037686fa55d1442796c9e96f998ddd1bff2a9fa13efe335e0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "eb5b5da2a66db140d6662c4f1eab035d7b6f2f1eee38da235dba7e76b57f655e", "generation_seconds_batch": 20.15202535991557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.177581787109375, "target_z": 0.8046874454919197, "ce": 5.982900142669678, "genuineness": 4.507347106933594, "identity": 0.7218868732452393, "hypothesis": "J'ai trouvé la petite boîte, elle était près, de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b76a0eb241df56c037686fa55d1442796c9e96f998ddd1bff2a9fa13efe335e0.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "b77dddf1d45a7c712703b5af9504b9cbb4eee1cfcea28f5b0346609baf43bfe5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "41d9ff063290fce5a1385de221836a659ff27f369fee8516032ad354e455731f", "generation_seconds_batch": 20.071417708997615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.498739719390869, "target_z": 2.2499997880807348, "ce": 6.292664527893066, "genuineness": 4.3881025314331055, "identity": 0.4381296932697296, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b77dddf1d45a7c712703b5af9504b9cbb4eee1cfcea28f5b0346609baf43bfe5.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "b77fdd0c573684cabad3223b968c7976cba8d93d3efd43ee207cb349465864ed", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "af18f8607bc1b892916c7ab41d11bf2ee7fb3e7e798e25716caa0309bab42464", "generation_seconds_batch": 15.060641168965958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2345082759857178, "target_z": 1.9609374760571985, "ce": 6.070269584655762, "genuineness": 4.482243061065674, "identity": 0.48852917551994324, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b77fdd0c573684cabad3223b968c7976cba8d93d3efd43ee207cb349465864ed.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "b8899fae976b505c1732776c613ca7b5114fa4e0b240fcfe33fdcf64886b01ae", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e544f316981c71232ec293f1f0ef29f932db7d950ab865e3fc8cc69d258e9955", "generation_seconds_batch": 15.864099674043246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3918237686157227, "target_z": 1.0390625891487295, "ce": 6.062326908111572, "genuineness": 4.055472373962402, "identity": 0.3737795650959015, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b8899fae976b505c1732776c613ca7b5114fa4e0b240fcfe33fdcf64886b01ae.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "b88edaa0959b6d479c9f79b8cc6339f50009e561d9fae1b0eebbca46555c96f4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8b2986783fb4cd186fa3f5f1d3ea7c9d0a345b9f12274c00d7cffcfbcce519d2", "generation_seconds_batch": 20.563803842058405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3204097747802734, "target_z": 0.9609375412631262, "ce": 5.847874641418457, "genuineness": 4.1998209953308105, "identity": 0.36943256855010986, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b88edaa0959b6d479c9f79b8cc6339f50009e561d9fae1b0eebbca46555c96f4.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "b89d3e53be5d2d7cafc061c84c002efa23a33f6a2dd529144a83dbc6513ce62f", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "aa1aaf67af7069d9dbf7d07e85ae7ad030882814803a4393e43470b41569b06f", "generation_seconds_batch": 16.65475852706004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.934774398803711, "target_z": 0.5390624913398377, "ce": 6.38797664642334, "genuineness": 4.105680465698242, "identity": 0.46035027503967285, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b89d3e53be5d2d7cafc061c84c002efa23a33f6a2dd529144a83dbc6513ce62f.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "b8d2fc9a2b27ba9899b2e28b653aef7ad210483a175a304f86cfc107289f7977", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "36e966d56e783c7dc0603f43997e7f2cf84b8e2a8eda6f419102753c46058df3", "generation_seconds_batch": 20.133378922007978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.127387523651123, "target_z": 1.8437501650525048, "ce": 5.903473377227783, "genuineness": 3.7542223930358887, "identity": 0.5011090040206909, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b8d2fc9a2b27ba9899b2e28b653aef7ad210483a175a304f86cfc107289f7977.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "b93c7987e291b48455d8f0e7ec64ed2609f4b27a71334cd53ab52a6c2dffd783", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7b4da0df84789083f8a3d266ae2af239e314af3d1d3d2a3e2b6aaa457983e78a", "generation_seconds_batch": 15.331332451081835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.149696350097656, "genuineness": 4.306513786315918, "identity": 0.1744844913482666, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b93c7987e291b48455d8f0e7ec64ed2609f4b27a71334cd53ab52a6c2dffd783.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": "b953772cbc09fdcab209e45f168e0ba99c6ae8b63e6dddabc2452d835dfcaf00", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "21d2409ce6428b98f7582d5e002d5dcf385e1ea9faa0bdd7278b40d137abd2a0", "generation_seconds_batch": 15.273313436075114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8883553743362427, "target_z": 0.48828128846130897, "ce": 6.348263263702393, "genuineness": 4.758388519287109, "identity": 0.4427870810031891, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi, quand nous pourrons parler?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b953772cbc09fdcab209e45f168e0ba99c6ae8b63e6dddabc2452d835dfcaf00.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "b95bf478af525b2a6cbbcd94d88c3f93a574f9d6a2434e51fd130a9049450f30", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "83957c43decf42e946d36bb4b099360855283b4da663611261ef999913b92c1b", "generation_seconds_batch": 17.599005733965896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5130228996276855, "target_z": 2.265625214975793, "ce": 5.772419452667236, "genuineness": 4.243753433227539, "identity": 0.39848679304122925, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b95bf478af525b2a6cbbcd94d88c3f93a574f9d6a2434e51fd130a9049450f30.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "b9b82c7f91c80ad0a0683639b8a22d498c3a85d7fc7377a4ce4e2b039bf7c567", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "89736bd804e5004204f3a60a4e721bdcaa7972e5acbdda5274793504439dca00", "generation_seconds_batch": 20.47471181396395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.116879940032959, "target_z": 0.7382812069538992, "ce": 6.022613525390625, "genuineness": 4.005263805389404, "identity": 0.29249992966651917, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b9b82c7f91c80ad0a0683639b8a22d498c3a85d7fc7377a4ce4e2b039bf7c567.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "b9c4f748c77de69dbd247b03e7240db41a0b71295dcbfd2dc1bdadb063e1f491", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "64890bf0f6a0a2d4f2e1eb8031cabf05d69e186d2571d596912cd07fbc734b7a", "generation_seconds_batch": 24.228062289999798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3275511264801025, "target_z": 0.9687499938869443, "ce": 6.165581703186035, "genuineness": 4.344170093536377, "identity": 0.022426389157772064, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/b9c4f748c77de69dbd247b03e7240db41a0b71295dcbfd2dc1bdadb063e1f491.mp3" }, { "id": "heldout-fr-1", "language": "fr", "sentences": [ "Les clés sont sur la table de la cuisine.", "J’ai regardé dans le tiroir... puis près de la fenêtre.", "Prends-les quand tu partiras." ], "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-1", "key": "ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Intense Interest. 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": "9e963ce72b570f6c1b4316401dd7627fb431c9adc05f393922f74fb49ed5c6bb", "generation_seconds_batch": 19.516648349002935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.3918492794036865, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "bac573bb172bb886bf2fe153544ef58c0ee71be6b175e6a62b7825c943c15de3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2f06d88d1fd94e4c22066e3e3229c69302a3d035f70758f2a4686189a162ab37", "generation_seconds_batch": 21.87726035201922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.313063621520996, "target_z": 2.04687497656662, "ce": 6.348263263702393, "genuineness": 4.331617832183838, "identity": 0.4279690682888031, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bac573bb172bb886bf2fe153544ef58c0ee71be6b175e6a62b7825c943c15de3.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "bb1c387ed65eee830d80f11032e7049f4865111fc2d3148ec5017994baf1dff4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30640a44db0c5e59822d1baf7d414bb276ff486c73dbd88db5ee5d8fec5e17ee", "generation_seconds_batch": 22.171814286964945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.784600257873535, "target_z": 1.4687498308721247, "ce": 6.3641486167907715, "genuineness": 4.080576419830322, "identity": 0.4057765007019043, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bb1c387ed65eee830d80f11032e7049f4865111fc2d3148ec5017994baf1dff4.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "bb3f3b0e1398a5e6feb45999b4d09e7a92d4abfebcd58c0468911cb5d8cb8c27", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8668e8f00e1d02990cb67609fecaa71ef3dda92f258d774b93e4f1c50a207d21", "generation_seconds_batch": 22.54940801288467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1561577320098877, "target_z": 0.7812500876204655, "ce": 6.157639026641846, "genuineness": 4.507347106933594, "identity": 0.6131551861763, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bb3f3b0e1398a5e6feb45999b4d09e7a92d4abfebcd58c0468911cb5d8cb8c27.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "bb465239973cfce5dc77d3b659b4dc4f7b4a354005c04e5c3ebbca3f1a855ff5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f9d61450b0f67e37b711fd004f9796383241e54ac5cf6d64de0e169ceaf83e13", "generation_seconds_batch": 21.470039712032303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4416089057922363, "target_z": 2.18750016709019, "ce": 5.855817794799805, "genuineness": 4.061748504638672, "identity": 0.6231070756912231, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bb465239973cfce5dc77d3b659b4dc4f7b4a354005c04e5c3ebbca3f1a855ff5.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "bc0c040a37cb281309c3e1cd7f01a6cbdbead1bc3afe6259ea573176f970bdaa", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "548ac989ab120ab03e3e4468ba8783604a09da8f63a0793945721c4cf57db063", "generation_seconds_batch": 16.585141211980954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1954352855682373, "target_z": 0.8242187074633205, "ce": 6.38003396987915, "genuineness": 4.15588903427124, "identity": 0.4250217080116272, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bc0c040a37cb281309c3e1cd7f01a6cbdbead1bc3afe6259ea573176f970bdaa.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "bcd4b36c770a767e804b9142b9873fe1a1e7ba716a5782799437bf023fae4007", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b4288a7176e820717d03df3b94db1d5fd1d2f2ac82f9f0d3588a82cbecd88efa", "generation_seconds_batch": 21.406646671006456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1559529304504395, "target_z": 1.874999975547777, "ce": 6.38797664642334, "genuineness": 4.3881025314331055, "identity": 0.4977816939353943, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bcd4b36c770a767e804b9142b9873fe1a1e7ba716a5782799437bf023fae4007.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "bd11dad1763c70562af2635cc9bb5ce0afb552b5db54082176dc37fd5003618f", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b3a7707650042793c7a326d2596ab5247a4a700e6c62f6826bcc8397cc0f4c23", "generation_seconds_batch": 15.77211151807569, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5132274627685547, "target_z": 1.1718750662247703, "ce": 5.831989288330078, "genuineness": 3.6663577556610107, "identity": 0.5548931360244751, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bd11dad1763c70562af2635cc9bb5ce0afb552b5db54082176dc37fd5003618f.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": "bd275dcbb038b89fe8dce22086b1e8727f2123ee6405517a6de1afc34523708f", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The road turns left behind the bridge.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c705244bf2e3e0f7da7ea8c5c98e8046fb7c8ca6f47f962f6a8a92c427a7e09", "generation_seconds_batch": 15.769169289036654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4560961723327637, "target_z": 1.1093749235868033, "ce": 6.403861999511719, "genuineness": 3.9676074981689453, "identity": 0.31770920753479004, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bd275dcbb038b89fe8dce22086b1e8727f2123ee6405517a6de1afc34523708f.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": "bd51675d879ba098f168881e8ceaed32c2b5ee2845bce5854bba80bb1c3fe04b", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Your message arrived after I had left.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6194395247cbe5199cd0d897b364378c69feb06e21aebad959c92292a81960e1", "generation_seconds_batch": 20.338151767035015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9276330471038818, "target_z": 0.5312500387160196, "ce": 6.372091293334961, "genuineness": 4.174716949462891, "identity": 0.45933714509010315, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bd51675d879ba098f168881e8ceaed32c2b5ee2845bce5854bba80bb1c3fe04b.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "bdd744165aa01e27642f9da712c7172423b144d000e669240fbd49612bd7fd9f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4f7bfe35e72ff5672a598c7881912c1067b7ba10079e308f7eb3a0cf2517b9b4", "generation_seconds_batch": 20.410871675005183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3275511264801025, "target_z": 0.9687499938869443, "ce": 6.125868320465088, "genuineness": 3.653805732727051, "identity": 0.47716060280799866, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bdd744165aa01e27642f9da712c7172423b144d000e669240fbd49612bd7fd9f.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "be7abdaa52fd3e1436d2fca1a499a50d90080f33374c0ff073e418381d91dd85", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ba462c183b649995fa075dd94f3527b66054bc861207c699c79c71fa87a04934", "generation_seconds_batch": 20.256252120947465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.520368814468384, "target_z": 1.1796875188485885, "ce": 6.157639026641846, "genuineness": 3.8169827461242676, "identity": 0.23673272132873535, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/be7abdaa52fd3e1436d2fca1a499a50d90080f33374c0ff073e418381d91dd85.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "bee2e9dd7447091618428ba8731b8ee00b24e152d8786159256d91d17e6da562", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "29ea4b4a37b67c2b6d5593f8ec971e5630f9270496e574d282723bc8fa41d6e1", "generation_seconds_batch": 17.7545624289196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.298780918121338, "target_z": 2.0312500713189836, "ce": 6.427689552307129, "genuineness": 4.469690799713135, "identity": 0.4629407823085785, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bee2e9dd7447091618428ba8731b8ee00b24e152d8786159256d91d17e6da562.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "bee32203401b27e8ce472bde9db2acb3c85b7529f7f45e3921fcb266ab266583", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28e54ffb1c52ae620bc2f9e2e2741e438bd68e6cbd8c931e9154ac6f0ce59d51", "generation_seconds_batch": 15.958877866039984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 6.125868320465088, "genuineness": 3.973883628845215, "identity": 0.497319757938385, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude draam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bee32203401b27e8ce472bde9db2acb3c85b7529f7f45e3921fcb266ab266583.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "bf4a5cede77fcf75e4ab73b750535fd93f7d85f88741d309e9af7464a48e91e9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4ee87d3842ca8ee761bde53feeb6d63b34580fbae525304aa0477130ed1a4151", "generation_seconds_batch": 19.860008836956695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2059426307678223, "target_z": 1.9296874047382149, "ce": 5.967014789581299, "genuineness": 3.9927117824554443, "identity": 0.22233256697654724, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bf4a5cede77fcf75e4ab73b750535fd93f7d85f88741d309e9af7464a48e91e9.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "bf7d88b23dc162e3c1bfdf00db9d2ccd068bfacaa29624b80161f01f82f999cb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "58ce5e30c19ad9e6b09ff5a867fb21de19be55c24f9fa58fa8cc504a7494a2bb", "generation_seconds_batch": 19.857672200072557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.484661817550659, "target_z": 1.140624994905787, "ce": 5.895530700683594, "genuineness": 3.5973212718963623, "identity": 0.4290693998336792, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/bf7d88b23dc162e3c1bfdf00db9d2ccd068bfacaa29624b80161f01f82f999cb.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "c007ec13f90e36ebf87b3da7fba2f8f93b7b0e568a4f0ffbb3f9aee3e6c53dfe", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d9225e0816140ea9644bb4cc53bda3cf02024c74aa70b5f6a85d9dcf0e522f3e", "generation_seconds_batch": 26.489686407032423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.898862838745117, "target_z": 1.593750116148059, "ce": 6.181467056274414, "genuineness": 4.394378662109375, "identity": 0.4907858371734619, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c007ec13f90e36ebf87b3da7fba2f8f93b7b0e568a4f0ffbb3f9aee3e6c53dfe.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "c15877d8fd210d7ef94b8df375ee462c790f48cdc8f5fbf12efb0cdc8ce87c21", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cf32929fa0c1b5b9a594615aa554ae8a0a306aace2ae461ca26e432537466c27", "generation_seconds_batch": 22.420462378067896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.798678398132324, "target_z": 2.5781248848707836, "ce": 5.780362129211426, "genuineness": 4.017816066741943, "identity": 0.495644748210907, "hypothesis": "I found the little box! It was beside the old window. We can look inside together!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c15877d8fd210d7ef94b8df375ee462c790f48cdc8f5fbf12efb0cdc8ce87c21.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "c28d6721e27fe665bb0820449fbf5081c4cd6b644f7a4e8dd257106a9a348646", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "db2fafb4f6549fa433a4878a5c9f49313347c6c47e998f7026fb417970146871", "generation_seconds_batch": 20.611205457011238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2202253341674805, "target_z": 1.945312309985851, "ce": 6.197352409362793, "genuineness": 4.344170093536377, "identity": 0.5457624793052673, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c28d6721e27fe665bb0820449fbf5081c4cd6b644f7a4e8dd257106a9a348646.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": "c2a57052fed5d3c026960b2b11e65265fdc0078359caf689d93c5539bde342fa", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The keys are on the kitchen table.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d2a981d9c14eb217822ea1e88e3cc6ea561f09a11e00440449cec3f8613ec0f", "generation_seconds_batch": 21.553609560942277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.541792869567871, "target_z": 1.2031248767200426, "ce": 6.173524379730225, "genuineness": 4.099404335021973, "identity": 0.3030010461807251, "hypothesis": "The keys are on the kitchen table. I checked a drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c2a57052fed5d3c026960b2b11e65265fdc0078359caf689d93c5539bde342fa.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "c2cc4c41863e96a86b8e8c318ce73e4727bf091577b8cab7cb6f3ab5eafa98e5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7f0a7c39bc1e8fb0d91211edda255ed7ea17f014fd420267e2662e82dace03f5", "generation_seconds_batch": 19.84002809296362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.363258123397827, "target_z": 1.007812517829746, "ce": 5.732706069946289, "genuineness": 3.8546390533447266, "identity": 0.43449485301971436, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c2cc4c41863e96a86b8e8c318ce73e4727bf091577b8cab7cb6f3ab5eafa98e5.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": "c3384d4b9b4b78708e1881acf304c05f6da658c7038952d2c63c617252b4a294", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e79d02d1c18454f0716d7e0401a1898752815eb4d84a4fcd424a475187bd2dcc", "generation_seconds_batch": 20.634393879096024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9919055700302124, "target_z": 0.6015625035659492, "ce": 6.125868320465088, "genuineness": 4.168440818786621, "identity": 0.4697139859199524, "hypothesis": "Ton message est arrivé après mon départ, je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c3384d4b9b4b78708e1881acf304c05f6da658c7038952d2c63c617252b4a294.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": "c35fd412769120fcbe055c40e2e125811492c7d7e4f7d12dabead2781ff77ee5", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a087c389364e1e9be1e867e35365dcfda0b462c42ec3f54e925c3ab3e083565", "generation_seconds_batch": 16.96798999106977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.663196563720703, "target_z": 1.3359373537960837, "ce": 6.157639026641846, "genuineness": 4.174716949462891, "identity": 0.6383953094482422, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c35fd412769120fcbe055c40e2e125811492c7d7e4f7d12dabead2781ff77ee5.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Intense Interest. 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": "1a3443892c9a66f1d50d952a9a6297bb7b1f74c42344cc7c97c01763dc40ae6f", "generation_seconds_batch": 16.646420339937322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0954556465148926, "target_z": 0.7148435882587337, "ce": 6.09409761428833, "genuineness": 4.545003414154053, "identity": 0.6553038358688354, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "c3b9955def8eae4ec42892acec249407b9431d51b4b9f295d1ca7029c792ea02", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fcd8d4a5182eedff46216410d829a6c593481fdbba8fcc0ceba6fd02b1e06b5b", "generation_seconds_batch": 15.376002733013593, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.198801279067993, "target_z": 1.9218749521143967, "ce": 6.117925643920898, "genuineness": 4.457139015197754, "identity": 0.4965367615222931, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c3b9955def8eae4ec42892acec249407b9431d51b4b9f295d1ca7029c792ea02.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "c3d4843f9a95c84d9e4e15497ba9e023afb1679448627f970749daff50ccb09a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8684e59d683818d433744525971605ba772060f5eaed820ecbf9724d32217860", "generation_seconds_batch": 19.768542892998084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.427325963973999, "target_z": 2.171875001018843, "ce": 6.252951145172119, "genuineness": 4.394378662109375, "identity": 0.4658905565738678, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c3d4843f9a95c84d9e4e15497ba9e023afb1679448627f970749daff50ccb09a.mp3" }, { "id": "heldout-nl-3", "language": "nl", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-3", "key": "c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Intense Interest. 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": "cce2b5928012070be3aef7766ef01ddc3267424d7225aae6e74b759abfe0bedc", "generation_seconds_batch": 17.890874278033152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3989651203155518, "target_z": 1.0468750417725474, "ce": 6.300607204437256, "genuineness": 4.419482707977295, "identity": 0.6873921155929565, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.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": "c4eab63d37d788c0533b3f78c75c3b39e289d150fcc66f10696e6b2882e8483c", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Someone moved the little blue chair.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1d9752d3e715644d97764041fe2985a49a1e9b99c6bf5e92de4aa776b63ea0fd", "generation_seconds_batch": 15.388404171098955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7274692058563232, "target_z": 1.4062499490578688, "ce": 6.38797664642334, "genuineness": 4.20609712600708, "identity": 0.5172411799430847, "hypothesis": "Someone moved the little blue chair. It used to stand here, beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c4eab63d37d788c0533b3f78c75c3b39e289d150fcc66f10696e6b2882e8483c.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": "c52fbdb2df9f1f7b0d8b71b0bc400b6402b6f949dcf619d6156881ec6a255443", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "495fadc0a1d4a2697fa0db82ad35830f51ba4c5ed940a7f68c3cbc89274387ea", "generation_seconds_batch": 16.977139194961637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6703381538391113, "target_z": 1.3437500672436131, "ce": 6.332377910614014, "genuineness": 4.356721878051758, "identity": 0.6383121013641357, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c52fbdb2df9f1f7b0d8b71b0bc400b6402b6f949dcf619d6156881ec6a255443.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "c593ce7e2e942b8d38ca964bc2df9d27bb9d47d8dfebefafd52045ef6eb9a7e0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "799fef2f8a0e02b7865f35c9ec4756541ed5576a8e45651eea53c9a23b157394", "generation_seconds_batch": 19.755011534085497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3846821784973145, "target_z": 1.0312498757012, "ce": 6.117925643920898, "genuineness": 4.174716949462891, "identity": 0.4627526104450226, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c593ce7e2e942b8d38ca964bc2df9d27bb9d47d8dfebefafd52045ef6eb9a7e0.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "c61c898fcaae2da462dadd68c59d93249d2c3c33e95ef115f0e9f3251b76c3bd", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "39ce993b5902c080654d785ae7de3daea32e5c3f4577f5d1a58f7d3a741b15d2", "generation_seconds_batch": 20.704770711949095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0418953895568848, "target_z": 0.6562500631682425, "ce": 6.316492557525635, "genuineness": 4.457139015197754, "identity": 0.45652860403060913, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c61c898fcaae2da462dadd68c59d93249d2c3c33e95ef115f0e9f3251b76c3bd.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "c6a1e6cbee00fd890b9225b433a83f75e14d2e33a31adb5fa7601652e1ff1965", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "01014ffca373d9561f19caf6dfc8c06421d5c406936a966986ea5fee71681d66", "generation_seconds_batch": 15.484136654995382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1597282886505127, "target_z": 0.7851561835205189, "ce": 6.1020402908325195, "genuineness": 4.356721878051758, "identity": 0.6626648306846619, "hypothesis": "La porte est encore éteint, 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/emo_Interest/c6a1e6cbee00fd890b9225b433a83f75e14d2e33a31adb5fa7601652e1ff1965.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "c75219c4c585e20160bd266505e5d04eac9ca8ce15a5525bcb7f2a200073d889", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c6cfde087ffff63c14f2dc927242b7602aed12a7f47835f6f1512cf90c70b05e", "generation_seconds_batch": 19.692197527037933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3382632732391357, "target_z": 0.980468803234527, "ce": 6.300607204437256, "genuineness": 4.149612903594971, "identity": 0.25209081172943115, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c75219c4c585e20160bd266505e5d04eac9ca8ce15a5525bcb7f2a200073d889.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "c75fa7da66f951fa08b82905b8b7cb7b4778e8d2aef27738d0bce6d6709dd513", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3cbbed892ded0cbc71f65c9acf79797a92ad48f12ef45d0b102a4012b9d3b75a", "generation_seconds_batch": 17.045546013046987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.470378875732422, "target_z": 1.1249998288344394, "ce": 6.09409761428833, "genuineness": 4.400654315948486, "identity": 0.5791534185409546, "hypothesis": "Je trouvais la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c75fa7da66f951fa08b82905b8b7cb7b4778e8d2aef27738d0bce6d6709dd513.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "c765dd565011c405b6d4a7b70b98c9d13808f5eeab6700d21fd687d68422cce3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0475658f5f9d475077a6313a2513154dfbaba2bfa2b9e921141877f2846ad158", "generation_seconds_batch": 15.102092346991412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3239803314208984, "target_z": 0.9648436371631796, "ce": 6.141753673553467, "genuineness": 4.281409740447998, "identity": 0.44302815198898315, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c765dd565011c405b6d4a7b70b98c9d13808f5eeab6700d21fd687d68422cce3.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": "c7d8e7b296b3095f65acfdd7f0418ccb0771f72bf8d6dcd269b086b9f279efc4", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0620e377733302aca0da0e5009bc01cf691c594199d2b1b971e58be3a4c1d4c", "generation_seconds_batch": 15.406588717014529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8347948789596558, "target_z": 0.4296875025471066, "ce": 6.1894097328186035, "genuineness": 4.482243061065674, "identity": 0.7621265649795532, "hypothesis": "La route tourne à gauche, après le pont, continue, jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c7d8e7b296b3095f65acfdd7f0418ccb0771f72bf8d6dcd269b086b9f279efc4.mp3" }, { "id": "heldout-nl-0", "language": "nl", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-0", "key": "c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Intense Interest. 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": "7931d85de1481e91db8b929f57547cf80f37e3b53b2cbaf29e451a60897a586f", "generation_seconds_batch": 15.881895263912156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.234713077545166, "target_z": 0.8671875881298868, "ce": 6.24500846862793, "genuineness": 4.281409740447998, "identity": 0.5714321732521057, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "c87e7edc759e1601840a6863e8c75b6cdb7808765157c8466cb0b6f4a9f3bd44", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f628b981c0195a0b58b4fd31caeb61491bcfa9bc75caf619ceb014337b76132a", "generation_seconds_batch": 22.23865743004717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.054384231567383, "genuineness": 4.218649387359619, "identity": 0.6276049613952637, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c87e7edc759e1601840a6863e8c75b6cdb7808765157c8466cb0b6f4a9f3bd44.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Intense Interest. 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": "373cfb5f82c21e57087a4c425369da105726cfc85aa36a2b66dc520684d18647", "generation_seconds_batch": 17.184532622923143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3168389797210693, "target_z": 0.9570311845393615, "ce": 6.459460258483887, "genuineness": 4.519899368286133, "identity": 0.3832908868789673, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "c93c3c0305a46221217e94552564633b029761ea664bafa55a06a7d28de80417", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bca4da0c0066678ba2ee5db2fa3cfa17ec18181c2ad35b047af0fd0655df1b1c", "generation_seconds_batch": 16.148321163025685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5701537132263184, "target_z": 2.328124835966338, "ce": 6.0146708488464355, "genuineness": 4.143336772918701, "identity": 0.6168464422225952, "hypothesis": "I found the little box! It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c93c3c0305a46221217e94552564633b029761ea664bafa55a06a7d28de80417.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "c94ecf1251b3f0501966d93996cae200d1c6028bc7c7d3f6f027b8a08bbdf5af", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "596047acde309ce3524971fbc79316d4eee98ca8cd000d09e45000cfa8fd8d96", "generation_seconds_batch": 20.74604876502417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1416702270507812, "target_z": 1.8593750703001408, "ce": 6.022613525390625, "genuineness": 4.1998209953308105, "identity": 0.5252691507339478, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c94ecf1251b3f0501966d93996cae200d1c6028bc7c7d3f6f027b8a08bbdf5af.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": "c9868a45fa374445c4b0ca0d1514300c8b30c0e5ebfa0c723b158355e2be6329", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb67c1e54a9e99abcf5257ec286b837f236be61ed2ffe9a086cedf2669b5c9ce", "generation_seconds_batch": 17.393045912962407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0488319396972656, "target_z": 1.7578124037193723, "ce": 6.062326908111572, "genuineness": 4.243753433227539, "identity": 0.5971214771270752, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c9868a45fa374445c4b0ca0d1514300c8b30c0e5ebfa0c723b158355e2be6329.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "c9997637ad7eadf5e8720112ad8de2631a3651cdd3b65bd5b6e2a52da682b770", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c4d6bb7bc49fd4059adaf84a2c80c597d8d9503538f4ce3f654e9fdab7dc4227", "generation_seconds_batch": 22.080986079992726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4918031692504883, "target_z": 1.1484374475296049, "ce": 6.09409761428833, "genuineness": 4.243753433227539, "identity": 0.5822609066963196, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c9997637ad7eadf5e8720112ad8de2631a3651cdd3b65bd5b6e2a52da682b770.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": "c9e91b479333c94f552bcdf715458b2ff95ec567b132ff98b618cab35306e8b8", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3599611a02c69f2c3549eea40cffe2d2eff06c043a0a4d3f607b3de5f886ce08", "generation_seconds_batch": 16.948172027012333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9274282455444336, "target_z": 1.6249999266433313, "ce": 6.260893821716309, "genuineness": 4.406930446624756, "identity": 0.8372952938079834, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/c9e91b479333c94f552bcdf715458b2ff95ec567b132ff98b618cab35306e8b8.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "ca13380cd5368864fd71be5b65382be5062e22092463aaa2ae76c091f36d96f4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fba57aa141bbb659dcf6a5d2187d558b5a10b31be856aa7ad8db5b5c795d62c", "generation_seconds_batch": 16.88421765109524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.498739719390869, "target_z": 2.2499997880807348, "ce": 5.518253803253174, "genuineness": 4.143336772918701, "identity": 0.379922091960907, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ca13380cd5368864fd71be5b65382be5062e22092463aaa2ae76c091f36d96f4.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "ca53ed5568f3121fa34ca22811a155eab1e228ce7611a1e0c39c365ffd986cc7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19f8a51346d59d233cd10c44e54858c74407e923f7916bf64a944b4467c61044", "generation_seconds_batch": 19.839591957977973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.191659927368164, "target_z": 1.9140624994905786, "ce": 5.974957466125488, "genuineness": 4.005263805389404, "identity": -0.13365031778812408, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ca53ed5568f3121fa34ca22811a155eab1e228ce7611a1e0c39c365ffd986cc7.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "ca5b7b9ae50470d1389762b3bde95edf4adc18e99347e4129304948feeda3e8a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ea8db7e423e7c42db44701f823ff24329514e4cb7515390a15ec7b90c7a3b2d7", "generation_seconds_batch": 20.31206647795625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7560348510742188, "target_z": 1.4375000203768524, "ce": 5.95112943649292, "genuineness": 4.18726921081543, "identity": 0.41845226287841797, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ca5b7b9ae50470d1389762b3bde95edf4adc18e99347e4129304948feeda3e8a.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "ca9fc0da36bcd1e3019fa13cb6c8a8bab84867ebb89e6ab98898b31531058213", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d3ede039cb83da2e468d75c57b5bbda553a49ea1a8edb02bc520b6987a907de1", "generation_seconds_batch": 23.13724829000421, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.070460796356201, "target_z": 0.6874998736635148, "ce": 6.316492557525635, "genuineness": 4.15588903427124, "identity": 0.16870111227035522, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ca9fc0da36bcd1e3019fa13cb6c8a8bab84867ebb89e6ab98898b31531058213.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": "cb5207608fd297663e4ffc5b975e7f2460e2c0b69de05b13e908faf866060cac", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed2e4539ee16f8317796488e0699404593ddbbd24a4ee3707dc8fae658456057", "generation_seconds_batch": 15.472160795005038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7417521476745605, "target_z": 1.4218751151292164, "ce": 6.149696350097656, "genuineness": 4.519899368286133, "identity": 0.6539241075515747, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre, prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cb5207608fd297663e4ffc5b975e7f2460e2c0b69de05b13e908faf866060cac.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "cbefa20a3265f76c8e35210a7e7488ae4812386a83e3fc7ea570646ffdcedaa6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "81e85ab8d46286bada8dc84552ad89cc1c2c97c8ea788f86cd7535012acc96d0", "generation_seconds_batch": 19.80117143294774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8843750953674316, "target_z": 2.671874838004023, "ce": 5.903473377227783, "genuineness": 4.268857479095459, "identity": 0.47427189350128174, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cbefa20a3265f76c8e35210a7e7488ae4812386a83e3fc7ea570646ffdcedaa6.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": "cc0c7e9c4d7a61487b1ee856606af9bf0c32f059b4b13e730155588b8ff7e004", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33eee44b2a42b70db7ea4f3f6ee955ac92331f31f1cca342d14df0b80b0def76", "generation_seconds_batch": 15.409346689004451, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8203072547912598, "target_z": 1.5078123548149263, "ce": 6.459460258483887, "genuineness": 4.607763767242432, "identity": 0.6091839671134949, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cc0c7e9c4d7a61487b1ee856606af9bf0c32f059b4b13e730155588b8ff7e004.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "cc1c46d464c056c269e7e6ff51c274babe8863f036f358c10f22710cd8be2a5f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ca52b909bd6492b0cebc28a51f49be9cb79c26a334c170cc9e7971a52a0ee96b", "generation_seconds_batch": 23.641709966002963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1383042335510254, "target_z": 0.7617188256490647, "ce": 6.054384231567383, "genuineness": 4.281409740447998, "identity": 0.5604703426361084, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cc1c46d464c056c269e7e6ff51c274babe8863f036f358c10f22710cd8be2a5f.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": "cc2d5f47bdbd79d59e1165c5fd118f7f0375be79fa1a5cbbb0e230d43e3d693e", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fbcff856c44ca9f744e5d50425408b1452c3475e3f285fd082775fb6178c2db0", "generation_seconds_batch": 20.634393879096024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.052607536315918, "target_z": 0.6679688725158253, "ce": 6.078212261199951, "genuineness": 4.293961524963379, "identity": 0.5387560725212097, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cc2d5f47bdbd79d59e1165c5fd118f7f0375be79fa1a5cbbb0e230d43e3d693e.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "cc3d6cfc25b9f65f69de89a9ea686b44a75c34ce6b590a50ba6d18c7eba284a1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "749c0ee990e984089872895b590e54376a638f8b8f7c8dc30b65d78c898f0843", "generation_seconds_batch": 21.204900555079803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5060858726501465, "target_z": 1.1640623527772411, "ce": 6.141753673553467, "genuineness": 4.287685871124268, "identity": 0.3087416887283325, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cc3d6cfc25b9f65f69de89a9ea686b44a75c34ce6b590a50ba6d18c7eba284a1.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "cc484e9e37654117c22d5c2fc66c669f5fd32b04b5369e3f3627bff13f56d632", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c136bbbc4566194bf2dc54c1d37c4c04f537402fe7b0edf484995f16536d35c6", "generation_seconds_batch": 16.122312884079292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1131045818328857, "target_z": 1.8281249989811574, "ce": 6.117925643920898, "genuineness": 4.243753433227539, "identity": 0.3442284166812897, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cc484e9e37654117c22d5c2fc66c669f5fd32b04b5369e3f3627bff13f56d632.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "cc752260e37d8a1c3bcc6a97001884cdeecc8bec4a175226e004b80c718395a6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3250fce8e243c1e68472416f309599e28b5276639592b6057a0bb1edd1533cf8", "generation_seconds_batch": 14.931687859003432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.34183406829834, "target_z": 0.9843751599582917, "ce": 5.839932441711426, "genuineness": 4.306513786315918, "identity": 0.40975016355514526, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cc752260e37d8a1c3bcc6a97001884cdeecc8bec4a175226e004b80c718395a6.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "ccb1b383d359440704d226768813bd3e160f73eb5a64f5ec3d286c37ccc94ae2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b7baeda49ab7446dcbc4bfcc41ad265f45de1f2028afb3ef8fcb53708bba6a1d", "generation_seconds_batch": 20.766324033029377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9702768325805664, "target_z": 1.6718751640336622, "ce": 6.141753673553467, "genuineness": 4.444586753845215, "identity": 0.6499724984169006, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ccb1b383d359440704d226768813bd3e160f73eb5a64f5ec3d286c37ccc94ae2.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "ccc7dac7176ab9046c0d606c207f1034d24ab2ea23c4fcacd193fdfd8504724f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f7919561db4bde2d30267a3e4ffe1119ef61d8f18822fa68dd4cc1fbe35cb471", "generation_seconds_batch": 18.354161667986773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9274282455444336, "target_z": 1.6249999266433313, "ce": 5.967014789581299, "genuineness": 4.250029563903809, "identity": 0.6208410263061523, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ccc7dac7176ab9046c0d606c207f1034d24ab2ea23c4fcacd193fdfd8504724f.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "cd017be542a2df12ad1bbb5a19c3a522d63ff0d64f7623c4f2f73fa703e13798", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bc8d1da1de21f40a43fda10aca7224ed1fa95574b89d03d0bb164503d13005ad", "generation_seconds_batch": 20.721114468062297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3703994750976562, "target_z": 1.015624970453564, "ce": 6.308549880981445, "genuineness": 4.231201171875, "identity": 0.6018779277801514, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cd017be542a2df12ad1bbb5a19c3a522d63ff0d64f7623c4f2f73fa703e13798.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "cd51cef29b642cdfb704ef3dcb187fb52ffbb58a2668af050748cac997dbbd2d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "63222eb481c4a3ed0889670e5a824742cae5e5c45f5234f67d977bf8565aa948", "generation_seconds_batch": 21.470039712032303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.55587100982666, "target_z": 2.3124999307187015, "ce": 5.780362129211426, "genuineness": 4.168440818786621, "identity": 0.4279414117336273, "hypothesis": "I found the little box! It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cd51cef29b642cdfb704ef3dcb187fb52ffbb58a2668af050748cac997dbbd2d.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "cd5ff78f69052256620ccafe699da47b205163926a2e1a2047bdcc9455f9db13", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4d475c698b7a339e8d63d9a1d3861a49d36792a8dd8c6567fb19a61986cd1d62", "generation_seconds_batch": 20.165152195026167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7488932609558105, "target_z": 1.429687306929323, "ce": 5.959072113037109, "genuineness": 4.024092197418213, "identity": 0.4363745450973511, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cd5ff78f69052256620ccafe699da47b205163926a2e1a2047bdcc9455f9db13.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "cd6243d7a29c2920e640ca6981679afc8635c698a326a3cf5b6937aa5b41b660", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "94c5badb808b53db1443452b853fb5d35ac750226d67b72477b7901e554f200f", "generation_seconds_batch": 21.357137451996095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6274895668029785, "target_z": 1.2968748298532822, "ce": 5.546053409576416, "genuineness": 3.553389072418213, "identity": 0.2971678376197815, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cd6243d7a29c2920e640ca6981679afc8635c698a326a3cf5b6937aa5b41b660.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "cd885704fdf1c4b4a677db65041bff6db3aa627f3ba20e0802808b9b566f771d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b772da4c47bb5a9a784848dad3916a32ee7d75b3bf1942c8e6f73bd1fbbd5807", "generation_seconds_batch": 20.447217168984935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9702768325805664, "target_z": 1.6718751640336622, "ce": 6.157639026641846, "genuineness": 4.055472373962402, "identity": 0.31403663754463196, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cd885704fdf1c4b4a677db65041bff6db3aa627f3ba20e0802808b9b566f771d.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "ce1702f31c20337ba9827eeb2a5f2e9f5647fce2c8ce99c0ce479444927c331f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b5caf2a4f50509ba958f0e6183c72222d36d9559aef211f51d538119d00983c2", "generation_seconds_batch": 15.134578297031112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.10973858833313, "target_z": 0.7304687543300812, "ce": 6.038498878479004, "genuineness": 4.3127899169921875, "identity": 0.5810527801513672, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ce1702f31c20337ba9827eeb2a5f2e9f5647fce2c8ce99c0ce479444927c331f.mp3" }, { "id": "heldout-de-3", "language": "de", "sentences": [ "Jemand hat den kleinen blauen Stuhl umgestellt.", "Er stand hier... neben dem hohen Bücherregal.", "Wir stellen ihn nach dem Essen zurück." ], "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-3", "key": "cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Intense Interest. 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": "8c623a221374d948d04ad497bd282c3f8050e4888d1229e1737b4d837e911b1f", "generation_seconds_batch": 15.50372493697796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245425224304199, "target_z": 0.8789063974774696, "ce": 6.467403411865234, "genuineness": 4.494794845581055, "identity": 0.6252315044403076, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "cfae46236059c8352a41ac2c88ad1ed9eaedb8eb612dc9b1d3f404793f2f2403", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cfd492fb04672db948daee455333d05b6d0093cfb98a722462086b3c8334734b", "generation_seconds_batch": 20.74604876502417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.670133590698242, "target_z": 2.437500215994636, "ce": 6.117925643920898, "genuineness": 4.268857479095459, "identity": 0.6042566299438477, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cfae46236059c8352a41ac2c88ad1ed9eaedb8eb612dc9b1d3f404793f2f2403.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "cfbbdcc8d7dc87e8bf5b6630f538c37e955521c743b349fe9ebdefe0f5b448fe", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c86534d4c781a7834f68bfe7a181a471ea8401cb1bbff0fc781f10a636ac2c5e", "generation_seconds_batch": 24.228062289999798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4918031692504883, "target_z": 1.1484374475296049, "ce": 6.022613525390625, "genuineness": 4.080576419830322, "identity": 0.5404086112976074, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cfbbdcc8d7dc87e8bf5b6630f538c37e955521c743b349fe9ebdefe0f5b448fe.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "cfd97555ab40637f81d9bb2afcd008e12150c5b151d02ba81b5b5c0f69c42cb2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7eb365b81f604a4000c323cb514eaad0a8282f5d04a10f259752d189e012d692", "generation_seconds_batch": 19.751068328972906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.598924160003662, "target_z": 1.2656250193580099, "ce": 6.268836498260498, "genuineness": 4.030367851257324, "identity": 0.7369734048843384, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/cfd97555ab40637f81d9bb2afcd008e12150c5b151d02ba81b5b5c0f69c42cb2.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "d00ce43a549aca8b6ed924adf46609374bb33f7bcbee5e1a34b80ba80f3856d7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0266c6d4f40e5bcd10366209f9902102bf12b3c1a08f9b389db6f216b508b7b7", "generation_seconds_batch": 15.060641168965958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.313063621520996, "target_z": 2.04687497656662, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.7887097597122192, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d00ce43a549aca8b6ed924adf46609374bb33f7bcbee5e1a34b80ba80f3856d7.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "d01558ae2ebfbcb55c037d77725bda575a7969e91ca89c231af15ee177459e0d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c2477f1ae5ccac426d4c720667d4ba6e3b8ddf5ae16492eb12550dcbb059566a", "generation_seconds_batch": 21.656958049046807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.370194911956787, "target_z": 2.1093751192045866, "ce": 5.816103935241699, "genuineness": 3.6914620399475098, "identity": 0.45923370122909546, "hypothesis": "The door is still open! I put your coat on the chair. Tell me when you are ready!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d01558ae2ebfbcb55c037d77725bda575a7969e91ca89c231af15ee177459e0d.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "d019e90f276fff52fbee19d23fed709343cef0eef39ee2ae46d8dc667eb56a86", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c0926e53f744096a4e0bcd2f9902943c7a8a95d798ea051a327c0daf86b3b733", "generation_seconds_batch": 21.003292822977528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1347334384918213, "target_z": 0.7578124689253001, "ce": 6.117925643920898, "genuineness": 4.507347106933594, "identity": 0.37132394313812256, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d019e90f276fff52fbee19d23fed709343cef0eef39ee2ae46d8dc667eb56a86.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": "d023d36984aa7fd5d5fc040cd81309c635f2ac2454eeffd6ec0a6914d3daf01f", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1fb93b4dbdccbd92d24da2d01c6ac9fd38978d9371e59fc34f40a1c1234a55dd", "generation_seconds_batch": 20.604242734028958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8702971935272217, "target_z": 1.5625000448290753, "ce": 6.221180438995361, "genuineness": 4.20609712600708, "identity": 0.7080819606781006, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder. Tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d023d36984aa7fd5d5fc040cd81309c635f2ac2454eeffd6ec0a6914d3daf01f.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "d04ff6efe66f5888fa6292db74cd3bd0d748594c8b7a4632ff4a2be0445bf564", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6bac272ba8126427577053f86bd11fff2c296588fde0d1eb6a1d1773c335a73b", "generation_seconds_batch": 19.77140656101983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3844776153564453, "target_z": 2.125000024452223, "ce": 6.23706579208374, "genuineness": 4.306513786315918, "identity": 0.37512052059173584, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d04ff6efe66f5888fa6292db74cd3bd0d748594c8b7a4632ff4a2be0445bf564.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "d058b7e8b1d8de856cf15a4b3e50c8584d4dbeb66f0f96ef9b7c31d7499cef1e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8c93c2e375e5b87ce1a9c17554342f82f0e69430dd007aa210a6e2c3bb4bd8bd", "generation_seconds_batch": 20.447217168984935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.606065511703491, "target_z": 1.273437471981828, "ce": 6.006728172302246, "genuineness": 3.9550557136535645, "identity": 0.18517668545246124, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d058b7e8b1d8de856cf15a4b3e50c8584d4dbeb66f0f96ef9b7c31d7499cef1e.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": "d104667abc78596dd6383ceba86b907eb609e2f81966779584a1ecb2df262cfa", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a6540baefa5a987b66d2fbe6d360d26d122b586b0df4d3bee4fa32c40b97e51", "generation_seconds_batch": 15.338630032958463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.541792869567871, "target_z": 1.2031248767200426, "ce": 6.149696350097656, "genuineness": 4.256305694580078, "identity": 0.6203184127807617, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d104667abc78596dd6383ceba86b907eb609e2f81966779584a1ecb2df262cfa.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "d10bda7b9cb2f235286427ada2ccd65550cd44e300bb6fd8b520614392dd35f8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "026bb408f840fe03bbd03a6a6e43aebf7e63f0d4d2dfb17b673ca27e45d67227", "generation_seconds_batch": 20.880165035952814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.784395694732666, "target_z": 2.5624999796231474, "ce": 5.974957466125488, "genuineness": 4.262581825256348, "identity": 0.5659849047660828, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d10bda7b9cb2f235286427ada2ccd65550cd44e300bb6fd8b520614392dd35f8.mp3" }, { "id": "heldout-en-4", "language": "en", "sentences": [ "I wrote the number on the envelope.", "Read it carefully... and check the last two digits.", "Call me when you have a moment." ], "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-4", "key": "d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00b3403a0b4d44d55f299ab3c245b6fde1c49aa2e84fb1eca7951d530b8ec25b", "generation_seconds_batch": 17.165115645038895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.913350224494934, "target_z": 0.5156250030565279, "ce": 6.395919322967529, "genuineness": 4.105680465698242, "identity": 0.43709781765937805, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "d16d0e3bb4607a1f0df53a856362181f6a7e10b08352e07ae329f81fed768268", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a539808fa250c05981c990987d3a978a22d94abd00d9d0ac9bf0867bd04aa7b3", "generation_seconds_batch": 20.213153827004135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.598924160003662, "target_z": 1.2656250193580099, "ce": 5.935244083404541, "genuineness": 4.036643981933594, "identity": 0.5441408157348633, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d16d0e3bb4607a1f0df53a856362181f6a7e10b08352e07ae329f81fed768268.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "d17694f24f918c3642a401a8d970ec99f8df6dca1ac93dab6833793acc00099a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cd8b56bc920a2afadec2aa06d0f6553e5130e20dcc8f1cae5971a2d4027fc554", "generation_seconds_batch": 20.013902019010857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 6.141753673553467, "genuineness": 4.149612903594971, "identity": 0.7605553865432739, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d17694f24f918c3642a401a8d970ec99f8df6dca1ac93dab6833793acc00099a.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": "d188e9f8f9bd89dd948995de36e83bdddd6d32ec1423942e3d7de5d08cc019a3", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c7efa1afb3ba58dafb75211ab187c3b7f83cd8883572782a64b92ac8d1131a6d", "generation_seconds_batch": 15.522001776960678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5703585147857666, "target_z": 1.2343749480390263, "ce": 6.165581703186035, "genuineness": 4.3127899169921875, "identity": 0.6317269206047058, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d188e9f8f9bd89dd948995de36e83bdddd6d32ec1423942e3d7de5d08cc019a3.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "d1a6e8d4df45502572d1a9e4feb71fc0436eac55e0cf247178a286461f8866a6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8b20c4df27a9d26a44724725b904c366201ef0b13f868c34f94226a4d1f6d590", "generation_seconds_batch": 19.33415228605736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5130228996276855, "target_z": 2.265625214975793, "ce": 6.165581703186035, "genuineness": 4.193545341491699, "identity": 0.5772557854652405, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d1a6e8d4df45502572d1a9e4feb71fc0436eac55e0cf247178a286461f8866a6.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": "d1cd81e03e7ca15d453215a40806c9a1b8d6152bf83beece8996d9ddaabdb1df", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7f9ef67ea9db7ce0038b46dd17419f9292cc6d5c9b218990dee760e26c72592c", "generation_seconds_batch": 17.703538216999732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7917418479919434, "target_z": 1.4765625443196542, "ce": 6.213237762451172, "genuineness": 4.168440818786621, "identity": 0.2782096862792969, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d1cd81e03e7ca15d453215a40806c9a1b8d6152bf83beece8996d9ddaabdb1df.mp3" }, { "id": "heldout-es-1", "language": "es", "sentences": [ "Las llaves están en la mesa de la cocina.", "Miré en el cajón... y luego junto a la ventana.", "Llévatelas cuando te vayas." ], "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-1", "key": "d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Intense Interest. 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": "556d7f4b5d0517a5c91c6795f93da16af57fa7a6e514b40661f109e9eb49d568", "generation_seconds_batch": 15.480531389010139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2704200744628906, "target_z": 0.9062501120726885, "ce": 6.38003396987915, "genuineness": 4.18099308013916, "identity": 0.6589096784591675, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "d2859e95b201553d446ead7705f78a0017957d5087a5852f80794c16fbe7b3e8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4beabd3d8ac41cfe6dc006618a903e410e81e801a5b84fd5ad468152c63e9f1f", "generation_seconds_batch": 22.54940801288467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302556276321411, "target_z": 0.9414062792917254, "ce": 6.197352409362793, "genuineness": 4.6203155517578125, "identity": 0.6810886263847351, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d2859e95b201553d446ead7705f78a0017957d5087a5852f80794c16fbe7b3e8.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "d2fb1c54e849ed8581ef50dfa9f57b4ede55056e16388e1501a8e4c68cf7a664", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85fce1a13c96bf87c4d39d0a58a9a8fa33492b6e52d3442323ea01058283079f", "generation_seconds_batch": 23.71006077993661, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0988216400146484, "target_z": 1.8124998329098099, "ce": 5.959072113037109, "genuineness": 3.835810661315918, "identity": 0.35620972514152527, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d2fb1c54e849ed8581ef50dfa9f57b4ede55056e16388e1501a8e4c68cf7a664.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "d3148310ba7d1ebcb3a071a7bb8e13020292ec86ed19c107b352e602692f4eff", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5c555717a16bd49d7bd17f443ef024c909cb76008220a9698464b820031d017b", "generation_seconds_batch": 20.48681285197381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.406106472015381, "target_z": 1.0546874943963656, "ce": 6.141753673553467, "genuineness": 4.268857479095459, "identity": 0.7923178672790527, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d3148310ba7d1ebcb3a071a7bb8e13020292ec86ed19c107b352e602692f4eff.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": "d3693dcab983168f8c82032e00e8b3cedb8c6952d7c2f1bdf6616d043ecd0cde", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8aef03d281b4af7b18b390e11c5579c6540aed74e85deccb3c638c980f9fbdc5", "generation_seconds_batch": 20.68333102890756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9774179458618164, "target_z": 1.679687355833769, "ce": 6.1894097328186035, "genuineness": 4.256305694580078, "identity": 0.5239508152008057, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d3693dcab983168f8c82032e00e8b3cedb8c6952d7c2f1bdf6616d043ecd0cde.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "d387124fdfe17ddfd34d01a84458de3a7e2ef6656345d483fefba8b5a4f0a792", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "312913d326c9ac27e9bb4ba47a12aa31de41bee7901d197a5d59650ce6cab22f", "generation_seconds_batch": 23.000849387026392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.241854429244995, "target_z": 0.8750000407537049, "ce": 6.403861999511719, "genuineness": 4.413206577301025, "identity": 0.6344232559204102, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d387124fdfe17ddfd34d01a84458de3a7e2ef6656345d483fefba8b5a4f0a792.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "d3aa08d98db33be199529362ff66f3ed2e56456b5b04b6270169e391e9ca0152", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d5f3c875f5b2e1bda605bb45707e46df290627b6cb7ecb8f0d3fd750ee919f95", "generation_seconds_batch": 15.271859729080461, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.313063621520996, "target_z": 2.04687497656662, "ce": 6.316492557525635, "genuineness": 4.293961524963379, "identity": 0.5022555589675903, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d3aa08d98db33be199529362ff66f3ed2e56456b5b04b6270169e391e9ca0152.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "d3c50b449f1fe5d2beaf9ba055555f529c73007db2d8fed7f72c3b73412bfb54", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1b0535d3a338cc025af8381f9e684c1aa5b6a0549b97a825d5f25dc8107cfc02", "generation_seconds_batch": 20.49043053202331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4989447593688965, "target_z": 1.1562501609771343, "ce": 6.046441555023193, "genuineness": 4.2751336097717285, "identity": 0.00889527052640915, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d3c50b449f1fe5d2beaf9ba055555f529c73007db2d8fed7f72c3b73412bfb54.mp3" }, { "id": "heldout-fr-4", "language": "fr", "sentences": [ "J’ai écrit le numéro sur l’enveloppe.", "Lis-le bien... et vérifie les deux derniers chiffres.", "Appelle-moi quand tu auras un moment." ], "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-4", "key": "d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Intense Interest. 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": "70e5bddbdfa271bee5676fd4878a266ee17b191ab7cd11a8ec9dc80aed169a90", "generation_seconds_batch": 17.918646815931424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0847437381744385, "target_z": 0.7031250397348623, "ce": 6.1020402908325195, "genuineness": 4.494794845581055, "identity": 0.8085770606994629, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "d4066afdf8d35fb70feee9cf21ff0766dd280e530bbbb6b1e15072842bd419cc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5b724b022f96b42ec384a312ec19927d3144c363743f8c983bc9dbbddcf413da", "generation_seconds_batch": 22.4887583340751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0845389366149902, "target_z": 1.7968749276621738, "ce": 6.332377910614014, "genuineness": 4.256305694580078, "identity": 0.4746488928794861, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d4066afdf8d35fb70feee9cf21ff0766dd280e530bbbb6b1e15072842bd419cc.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": "d45fdfa871e7a264f642f54981aec8763dabbf97498ba09427757fe10d57161b", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f17205e1cb99afdaba8998f6df9dfb494f4da6a68b3a76dfd2a09872000627a0", "generation_seconds_batch": 20.626700583961792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2632784843444824, "target_z": 0.8984373986251591, "ce": 5.919358730316162, "genuineness": 4.457139015197754, "identity": 0.5801711082458496, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d45fdfa871e7a264f642f54981aec8763dabbf97498ba09427757fe10d57161b.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "d496a4be13d039df563f87701d66492d360edcbac380cf77016c00297ef99bd8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5a967646af2460adf79d0f93e5a24c5c35627a140336999b31289decb5bef9ab", "generation_seconds_batch": 21.3932950750459, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.120450735092163, "target_z": 0.7421875636776639, "ce": 6.229123115539551, "genuineness": 4.457139015197754, "identity": 0.5291252136230469, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d496a4be13d039df563f87701d66492d360edcbac380cf77016c00297ef99bd8.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "d4cc6f213d18a4c9bb9f6dbbabc110ca78bcdf8e3f362cdebfa9ee49b45bf5f2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "51e13befeb607f7a75da9c5850945b052e0252099c2187fe48d8aebb33b8ff49", "generation_seconds_batch": 15.215991965029389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.841731548309326, "target_z": 1.5312499735100917, "ce": 6.2767791748046875, "genuineness": 4.3881025314331055, "identity": 0.6057294011116028, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d4cc6f213d18a4c9bb9f6dbbabc110ca78bcdf8e3f362cdebfa9ee49b45bf5f2.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "d5151e8eb1e01e9e8965821c7f52c5471e61c93724e263b714157d662b88f140", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8e9bdacbef8f789c84af3f718f22707c0b5603334e1fd9dad310b7d8503fee56", "generation_seconds_batch": 23.348749800934456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0740315914154053, "target_z": 0.6914062303872796, "ce": 6.221180438995361, "genuineness": 4.469690799713135, "identity": 0.33537453413009644, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d5151e8eb1e01e9e8965821c7f52c5471e61c93724e263b714157d662b88f140.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "d51bb360a48024007a13588f9ad44ab85a981e96dfc45863f73852a653a362db", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0d2eeef1c1737090b9bcdee793a87029b84b76f12cd9ebd820d8da9b45b3c29a", "generation_seconds_batch": 19.910861787036993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6917624473571777, "target_z": 1.3671876859387786, "ce": 6.300607204437256, "genuineness": 4.168440818786621, "identity": 0.29273611307144165, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d51bb360a48024007a13588f9ad44ab85a981e96dfc45863f73852a653a362db.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "d5324aed7fc93b1691d9afe3112bc6a9081a99447e055f4f48f447f74a228f61", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "eb00f964311d467b8ac1d2f972e2d61257aaad6f8cc16705696d18e87bae2495", "generation_seconds_batch": 23.83501401299145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8560142517089844, "target_z": 1.546874878757728, "ce": 6.054384231567383, "genuineness": 3.9173994064331055, "identity": 0.12521426379680634, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d5324aed7fc93b1691d9afe3112bc6a9081a99447e055f4f48f447f74a228f61.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "d56f4047ab6c3a6a80b414ac0631a5d8e1b4176c9a7609405671743e3be130dc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c226a640f5e4451e077a07c5bb4aafc1d64f1034863fd0fc6206fc26d71c6ac1", "generation_seconds_batch": 22.0735661649378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6917624473571777, "target_z": 1.3671876859387786, "ce": 6.324435234069824, "genuineness": 4.149612903594971, "identity": 0.6652642488479614, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt. Des choses ma oucho", "wer": 0.2222222222222222, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d56f4047ab6c3a6a80b414ac0631a5d8e1b4176c9a7609405671743e3be130dc.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "d5aabe544641edd58d7d346de059b53c62869f1c3d718e8ec2b20095ca5bf757", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3ab03a3bc36c073361760dcdd12669628e7d90d9b2718bd5f79a3506f01ae773", "generation_seconds_batch": 20.478779423981905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.770317554473877, "target_z": 1.4531249256244885, "ce": 5.990842819213867, "genuineness": 4.118232727050781, "identity": 0.4109008014202118, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d5aabe544641edd58d7d346de059b53c62869f1c3d718e8ec2b20095ca5bf757.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "d6454a7dec9920db211337ea77ab023891c08415b1e75814f33c075fe8fbbe44", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1d189e4c1fe30621dd1c15ce9b47b81ced1f25eb5c007d8339937e472fbceb9f", "generation_seconds_batch": 15.441131678991951, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3989651203155518, "target_z": 1.0468750417725474, "ce": 6.348263263702393, "genuineness": 4.093128204345703, "identity": 0.24040530622005463, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d6454a7dec9920db211337ea77ab023891c08415b1e75814f33c075fe8fbbe44.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "d6611f036432fa2aefea7f5c016cd642190678ba0d9d9aff4d1101eaf1ab24b8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ccc9f5384f28382e31b87bd3cf6dcc7624ec9fd10e4755ccee2ed77202ba330f", "generation_seconds_batch": 14.813869612989947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6846208572387695, "target_z": 1.3593749724912492, "ce": 6.268836498260498, "genuineness": 4.356721878051758, "identity": 0.6037255525588989, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d6611f036432fa2aefea7f5c016cd642190678ba0d9d9aff4d1101eaf1ab24b8.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "d6831bc637337b8c7825d730e66890edee322149d1ea8123cb7b45a7e196343d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d62b9a35f3e91059de5f95743f78f6fcaca3cd0d2dda7e7bc3fe10e33b511c1f", "generation_seconds_batch": 21.217900724965148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7917418479919434, "target_z": 1.4765625443196542, "ce": 5.824047088623047, "genuineness": 4.13078498840332, "identity": 0.5996748208999634, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d6831bc637337b8c7825d730e66890edee322149d1ea8123cb7b45a7e196343d.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "d6f6914d6b85e674d20c33f6e728ba1ed06e215ffdd21eff4218a287d2a08447", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a0d944011c3b0a478357ae81067f35865f4d4adffd902111659614760e90a043", "generation_seconds_batch": 20.93570679507684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.420389175415039, "target_z": 1.0703123996440018, "ce": 6.197352409362793, "genuineness": 4.337893962860107, "identity": 0.4490818977355957, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d6f6914d6b85e674d20c33f6e728ba1ed06e215ffdd21eff4218a287d2a08447.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "d6f9fc85476d99c00fc607349e0d79d5b2e0631a474ef8f1fd658dad56f20b5d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f42f239ab6ef6e31bb8803a0e35f04b2152f523a06dc3fb7778144acb957dac6", "generation_seconds_batch": 20.324017529026605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2561371326446533, "target_z": 0.890624946001341, "ce": 6.157639026641846, "genuineness": 4.494794845581055, "identity": 0.49315446615219116, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d6f9fc85476d99c00fc607349e0d79d5b2e0631a474ef8f1fd658dad56f20b5d.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "d72aba42f7d25650300c235b11a4a4db140da69b60d99b9c8265c2d7906b6740", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "95e2a5f1183dcd2cf39c6ebe5e1f0c09091a309559b2841b7f4696fb6ce63492", "generation_seconds_batch": 23.000849387026392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1347334384918213, "target_z": 0.7578124689253001, "ce": 6.435632705688477, "genuineness": 4.080576419830322, "identity": 0.3101796507835388, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d72aba42f7d25650300c235b11a4a4db140da69b60d99b9c8265c2d7906b6740.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "d731426d8a2e92c118516f9e249176c786f136d5834137ecf41798e8c722801c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "219375a1280c7f2673e778441774372e21d0dd405d8fd8db00542a49453d7eba", "generation_seconds_batch": 14.883428246015683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2704200744628906, "target_z": 0.9062501120726885, "ce": 5.982900142669678, "genuineness": 3.8420867919921875, "identity": 0.3785337805747986, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d731426d8a2e92c118516f9e249176c786f136d5834137ecf41798e8c722801c.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "d785e9ee6a0dfa130aad64b2a10d501765515189d76e2c333d33e3ff53d9a9aa", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9046ea84a9d49b643f7020047ab8553305be707234acfab79bf248506e12eddb", "generation_seconds_batch": 20.586263173958287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0274078845977783, "target_z": 1.734375045847918, "ce": 6.348263263702393, "genuineness": 4.381826400756836, "identity": 0.5201948881149292, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d785e9ee6a0dfa130aad64b2a10d501765515189d76e2c333d33e3ff53d9a9aa.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "d786475ce5b389fa5400c645f38c8e9432611fcebeb1885c82b0b715175e5e8f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6577b192fffb5f618e5a8ea9228c9ecc09333a3469af54b1b82ac2bc172afb68", "generation_seconds_batch": 21.613487274968065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.534651756286621, "target_z": 1.195312684919936, "ce": 5.546053409576416, "genuineness": 3.810706615447998, "identity": 0.27610933780670166, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d786475ce5b389fa5400c645f38c8e9432611fcebeb1885c82b0b715175e5e8f.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "d7ca01140eefd5dce39696134f4938bb7ee18f458fa9d4e69f8dfb9a6611ac0f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9d0136da1fd3c87730389e5ea1afc0565568c8c74721c96f4c95833557ba18ab", "generation_seconds_batch": 16.353988536982797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.841731548309326, "target_z": 1.5312499735100917, "ce": 6.038498878479004, "genuineness": 3.8295347690582275, "identity": 0.4679027795791626, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d7ca01140eefd5dce39696134f4938bb7ee18f458fa9d4e69f8dfb9a6611ac0f.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "d846240d869ef8e0f3fcdbaa5e23505e5f9e13f425c74cbc1f28d2aecb223acb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e7f73f50015cfd926a36cdb5b5f39980e8bed73e786cac4394df9906d0795ceb", "generation_seconds_batch": 22.19759489397984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3703994750976562, "target_z": 1.015624970453564, "ce": 6.467403411865234, "genuineness": 4.419482707977295, "identity": 0.40332120656967163, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d846240d869ef8e0f3fcdbaa5e23505e5f9e13f425c74cbc1f28d2aecb223acb.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "d86cb9db0880443a366b5704ddfd49e2d454a93864600dc08dba7da32cad2372", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4e5c4b1c029e3139d96a71eeefd2d43ab0d8269c00946ca24ca511e3a23f6ef4", "generation_seconds_batch": 20.47471181396395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6203484535217285, "target_z": 1.2890626380531753, "ce": 6.205295085906982, "genuineness": 4.017816066741943, "identity": 0.6029927730560303, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d86cb9db0880443a366b5704ddfd49e2d454a93864600dc08dba7da32cad2372.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "d870676ac573894e41719d2a2bfbca4994add4208a9bdda4a591e0973e200e4e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "68696407b94914022e6cf330f633a04669833455a44a72f0c2557360d2811489", "generation_seconds_batch": 19.77644963003695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2702152729034424, "target_z": 2.0, "ce": 6.038498878479004, "genuineness": 4.319066047668457, "identity": 0.4897793233394623, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/d870676ac573894e41719d2a2bfbca4994add4208a9bdda4a591e0973e200e4e.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "da823018bcb6b6375eb67dd068db159ce83152907130b84cda9ca9b99a00c988", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ef04eddc4b1842e9daf166aa1ab0b85ba5508cead9fab9ca0682c8834fd1bf5d", "generation_seconds_batch": 20.454305037041195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.149696350097656, "genuineness": 4.118232727050781, "identity": 0.741363525390625, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/da823018bcb6b6375eb67dd068db159ce83152907130b84cda9ca9b99a00c988.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "dad21fc53e774f185bc08a104139c397f6108e51b53f51db8916dd5d04697f87", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "509e56a77dc8ad6f3f2d8a81305a741610eb88db584f29c5d31d6a9ef86b2e71", "generation_seconds_batch": 22.171814286964945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.720327854156494, "target_z": 1.398437496434051, "ce": 6.3641486167907715, "genuineness": 4.20609712600708, "identity": 0.4766903221607208, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dad21fc53e774f185bc08a104139c397f6108e51b53f51db8916dd5d04697f87.mp3" }, { "id": "heldout-en-0", "language": "en", "sentences": [ "Your message arrived after I had left.", "I read it twice... before putting the phone away.", "Let me know when we can talk." ], "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-0", "key": "db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Intense Interest. 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": "d281e27c36492a9fbb7d424bfa8a3a3687605e05e376a6f738c00532e9efed26", "generation_seconds_batch": 16.896964655956253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7580249309539795, "target_z": 0.3457031803995676, "ce": 6.38797664642334, "genuineness": 4.494794845581055, "identity": 0.17308226227760315, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "dbd04c89f51c2cbaebb09b90adc7d9a2d76ea19a783fc41c8661748ebea3be1a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ef33a7fc2d7206b06b30976de5cb358c5d2ca3b73d20f8c80eb2a7189267ae76", "generation_seconds_batch": 19.768542892998084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.013124942779541, "target_z": 1.7187498797765706, "ce": 6.38003396987915, "genuineness": 4.149612903594971, "identity": 0.4256255030632019, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dbd04c89f51c2cbaebb09b90adc7d9a2d76ea19a783fc41c8661748ebea3be1a.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "dbdf8b85f1f90686b6baf09265e1a751c4324936cbbef60d380509ec9c74f75b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0aeee404680d8d49efdd5b25c4f7edec45248a1ec6de181f7a8428f89a1ec70d", "generation_seconds_batch": 22.293617054936476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5560758113861084, "target_z": 1.2187500427913902, "ce": 6.141753673553467, "genuineness": 4.300237655639648, "identity": 0.5662449598312378, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dbdf8b85f1f90686b6baf09265e1a751c4324936cbbef60d380509ec9c74f75b.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "dc2e8f8c2c7fd63547fe50cc718ac88354a52ad075178c55fb10fbef715edaed", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f6311891170a25d82485804eb1d88fba7c999e84a56009eddde732ecd2b7636", "generation_seconds_batch": 23.177062809932977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2844982147216797, "target_z": 2.0156251660713473, "ce": 5.736677646636963, "genuineness": 3.923675537109375, "identity": 0.54142826795578, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dc2e8f8c2c7fd63547fe50cc718ac88354a52ad075178c55fb10fbef715edaed.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "dc8ea2e76b36e0742de01f0825286eaa608d9710ce2018e1126fb21339f48b8c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0beb65821f46dbe399b9fcdccabd4d5fc5f399af1bd4a6fcc9b36d32ec61d356", "generation_seconds_batch": 21.360249279998243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3703994750976562, "target_z": 1.015624970453564, "ce": 6.348263263702393, "genuineness": 4.218649387359619, "identity": 0.7104370594024658, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dc8ea2e76b36e0742de01f0825286eaa608d9710ce2018e1126fb21339f48b8c.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "dc91ef1daef156ee2c2d7660efb5a7f9b665bf266be94bfc574929b67b726859", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "92086c71fea3580baffdedd67d0c17d3f11262b1de583830a40426f63d0504d9", "generation_seconds_batch": 20.811868298915215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.898862838745117, "target_z": 1.593750116148059, "ce": 6.054384231567383, "genuineness": 4.268857479095459, "identity": 0.5318776965141296, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dc91ef1daef156ee2c2d7660efb5a7f9b665bf266be94bfc574929b67b726859.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": "dd2decca0805944fe09d67b384bf0a688406908baac179fdeb7c063a4e5a7d63", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "56ca1f7d30af90234e2c60e46cbd852e036c4debe93606b436d0a2727b77c1eb", "generation_seconds_batch": 17.001222103019245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7560348510742188, "target_z": 1.4375000203768524, "ce": 6.125868320465088, "genuineness": 4.287685871124268, "identity": 0.5566890239715576, "hypothesis": "Ik schreef het nummer op de envelop, lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dd2decca0805944fe09d67b384bf0a688406908baac179fdeb7c063a4e5a7d63.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": "dd8a1a7086bbf38ebea412904f287db5556c2e59734508fc0bcc221286bf4a3f", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Someone moved the little blue chair.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "74f1962f92844f491511bc8a56a556745aeef8ed1e24f7b42569578306a5ec69", "generation_seconds_batch": 21.085157086024992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 6.3641486167907715, "genuineness": 4.1998209953308105, "identity": 0.4026114344596863, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dd8a1a7086bbf38ebea412904f287db5556c2e59734508fc0bcc221286bf4a3f.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "ddd99c9c062071dc3f1beb85869cbf8bb7672024e2c58db803ce86330794e561", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4c554684ec14a62c1b25a90e6b304410322ae6a2521f94e3754e926076b1d693", "generation_seconds_batch": 19.7807517379988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.727264404296875, "target_z": 2.4999998369851806, "ce": 6.117925643920898, "genuineness": 4.444586753845215, "identity": 0.3770769536495209, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ddd99c9c062071dc3f1beb85869cbf8bb7672024e2c58db803ce86330794e561.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "dddf283199497ff0b148280f21aea1f22ef736a7378a8fa7b1bc8894e9832e11", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2e2a6b316e2ee51856034bf3f45c043f2e0f19f507c8e2a26e76d5a7560263a6", "generation_seconds_batch": 20.760876609012485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3775408267974854, "target_z": 1.023437423077382, "ce": 6.316492557525635, "genuineness": 4.545003414154053, "identity": 0.5574809908866882, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dddf283199497ff0b148280f21aea1f22ef736a7378a8fa7b1bc8894e9832e11.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "ddf2d8843bff6641b433b8dcdb63eadffe5e0ba135a2ee1ed9e8a4670a0edf4a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "85ad49e158424643a03e2e7cbf4a036031ac9db23bec9badc0d501d159978f27", "generation_seconds_batch": 19.751068328972906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.656055450439453, "target_z": 1.3281251619959769, "ce": 6.316492557525635, "genuineness": 4.400654315948486, "identity": 0.5839220285415649, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ddf2d8843bff6641b433b8dcdb63eadffe5e0ba135a2ee1ed9e8a4670a0edf4a.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "de9be99fda14ac26e0f424efdd44a93abbb1110a97b87623c0b5b58f91eb1c6d", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9df4e0f59709b90667627973395647fa154644312944c517a34feb1a8f0cd83f", "generation_seconds_batch": 19.921709978953004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.484457015991211, "target_z": 2.2343748828330985, "ce": 6.149696350097656, "genuineness": 4.3127899169921875, "identity": 0.6291031837463379, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/de9be99fda14ac26e0f424efdd44a93abbb1110a97b87623c0b5b58f91eb1c6d.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "dee4122aee737b89e532e7362c0c19d0360d79952d37e15ba59a071778e4d5ed", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e58cf83bc2757dae0de9443cc54ee75b64f4bb1e959cb2efb182e478213f1e9d", "generation_seconds_batch": 23.71006077993661, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4701743125915527, "target_z": 2.218749977585462, "ce": 5.744620323181152, "genuineness": 3.973883628845215, "identity": 0.04813738167285919, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dee4122aee737b89e532e7362c0c19d0360d79952d37e15ba59a071778e4d5ed.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "df0dc01f1a116ab7030a8042ea344998167958e0cc82b695b3275f595d9806c7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d4599758a5361ebfe4e50d8776421b6bce1f1843fbb9b8d06b33039a7848937f", "generation_seconds_batch": 22.002744075027294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.227571487426758, "target_z": 0.8593748746823575, "ce": 6.205295085906982, "genuineness": 3.9173994064331055, "identity": 0.4316786825656891, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/df0dc01f1a116ab7030a8042ea344998167958e0cc82b695b3275f595d9806c7.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "df3aabccb438af85a9542b5523827062f7e2c1c56d1a6e8e52fd287633513614", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "36f0880d26943cf0ad64a52810ff819a3115d20bf556c352a909e105dbc7c95c", "generation_seconds_batch": 19.756566883064806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6346311569213867, "target_z": 1.3046875433008114, "ce": 6.109982967376709, "genuineness": 4.444586753845215, "identity": 0.6018199920654297, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/df3aabccb438af85a9542b5523827062f7e2c1c56d1a6e8e52fd287633513614.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "df6945d721899b6b02f49f5219d410e46d1062050eedcd7a6ed5a292b8f1bdbd", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "38ecfdab8e9a8bf692f50fbbeb02d6f85b3523eb1d0a03ac80a4b1958c562381", "generation_seconds_batch": 21.218467638944276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8631558418273926, "target_z": 1.5546875922052572, "ce": 6.1894097328186035, "genuineness": 4.20609712600708, "identity": 0.5284509658813477, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/df6945d721899b6b02f49f5219d410e46d1062050eedcd7a6ed5a292b8f1bdbd.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "dfc6d8247304b8d8b06a11ec5a105ef579d83bff088babd931151533e0863c67", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fc9409c3b97d5560748803bb56e7c74ec4a00e7248cd9e2a70e2f8c675a8501f", "generation_seconds_batch": 15.7738140639849, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5130228996276855, "target_z": 2.265625214975793, "ce": 6.078212261199951, "genuineness": 4.042920112609863, "identity": 0.25414958596229553, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dfc6d8247304b8d8b06a11ec5a105ef579d83bff088babd931151533e0863c67.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "dfc97dcbd7d0315639ad27c063e2bb9c306fbe3b13e1581086dabbcca4867f89", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ffa1d6770e486a6a02848feb24f1a8ad030004e285dc162a78f93aca9e6709b9", "generation_seconds_batch": 23.912906158948317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.125868320465088, "genuineness": 4.024092197418213, "identity": 0.3257904350757599, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dfc97dcbd7d0315639ad27c063e2bb9c306fbe3b13e1581086dabbcca4867f89.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": "dff429d1eb61245d3c1928818495902ff6015df67047dfff6d14f33ab0b9dc2a", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Your message arrived after I had left.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8266deee5ee0c7c188bccfaafd89c9fe0d1fa77949ca3aaff948170bf9767f08", "generation_seconds_batch": 15.51565354410559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2632784843444824, "target_z": 0.8984373986251591, "ce": 6.284721851348877, "genuineness": 4.011539936065674, "identity": 0.4672008752822876, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/dff429d1eb61245d3c1928818495902ff6015df67047dfff6d14f33ab0b9dc2a.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": "e00a6392ed6ce69588629e02081e8f833cf82efb80d910fe02877c79fd1e82f9", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ef37d5dcf70a6c1a9a720c4d93a63d6d5982d008ada2da2d43ac2a8fc8da490", "generation_seconds_batch": 15.268667532945983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6346311569213867, "target_z": 1.3046875433008114, "ce": 6.3641486167907715, "genuineness": 4.519899368286133, "identity": 0.7866058349609375, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg, sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e00a6392ed6ce69588629e02081e8f833cf82efb80d910fe02877c79fd1e82f9.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": "e03ea9d0f695536374f81fdf67b462b9198ccd07b2532001ec6d879c734928f1", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dad32efc20219ff184372c0e9be2923490c93f397cedc625bf0732d89e07e657", "generation_seconds_batch": 15.3320644950727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8060245513916016, "target_z": 1.4921874495672902, "ce": 6.268836498260498, "genuineness": 4.344170093536377, "identity": 0.4656858444213867, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal. Dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e03ea9d0f695536374f81fdf67b462b9198ccd07b2532001ec6d879c734928f1.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "e057eab77d1317936baea502d51ab9adb8ea9c762b8e7dad02253c4f782ca569", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9200963fed4c599b6d8c6800338d6bb4a22f3e6611ad6205cf1d3513a5796e38", "generation_seconds_batch": 20.14129800896626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9919055700302124, "target_z": 0.6015625035659492, "ce": 6.435632705688477, "genuineness": 4.293961524963379, "identity": 0.3155773878097534, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e057eab77d1317936baea502d51ab9adb8ea9c762b8e7dad02253c4f782ca569.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "e0b81f04a17d1a0ab78d49db0741b3b40c624f0ab2eb9a1de8ede36def803345", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9c5abfaebdb8fc06ec6ee229f168283290bf7f20ee36aa826a8e60eabfca2afe", "generation_seconds_batch": 22.47596691409126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6917624473571777, "target_z": 1.3671876859387786, "ce": 6.229123115539551, "genuineness": 4.287685871124268, "identity": 0.5233493447303772, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e0b81f04a17d1a0ab78d49db0741b3b40c624f0ab2eb9a1de8ede36def803345.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "e11632cba242177711602039afdce0d8067a776d53109b35ef3871f7cd6f3950", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5bac98eec144a36c8488660f3d38e484c99a75ed25a06323f63fd1057311e023", "generation_seconds_batch": 16.885390685056336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8488731384277344, "target_z": 1.5390626869576212, "ce": 6.1894097328186035, "genuineness": 4.306513786315918, "identity": 0.179549440741539, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e11632cba242177711602039afdce0d8067a776d53109b35ef3871f7cd6f3950.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": "e1504f49501877622291751c6e083a4c810dba788921d777c6b7ba391c3793f9", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d33304929c66914edbd6e74e32e0229d31740659807eec98e955c828b71cea10", "generation_seconds_batch": 20.756239845068194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.463237762451172, "target_z": 1.1171876370343328, "ce": 6.157639026641846, "genuineness": 3.9299514293670654, "identity": 0.1804800033569336, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e1504f49501877622291751c6e083a4c810dba788921d777c6b7ba391c3793f9.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "e1625be66229250dd35db9ce00cdbc1fcd8e93dcb80feac219b18d2e2417ac50", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "20f94ff7a417f4f9e2f26204a9890d17daac13065386a7562d46379bba9b49a7", "generation_seconds_batch": 20.244457046967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7988831996917725, "target_z": 1.484374996943472, "ce": 6.149696350097656, "genuineness": 4.042920112609863, "identity": 0.22253073751926422, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e1625be66229250dd35db9ce00cdbc1fcd8e93dcb80feac219b18d2e2417ac50.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "e175a227909786afd307588adfa7f185ad6bbd8b0f62e12072b62b4907c6e9a0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fc883cbe386b8cb6c749163dba6692d7cab6b37bffe7b3bac47e2b5c1019e226", "generation_seconds_batch": 19.893245415994897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6917624473571777, "target_z": 1.3671876859387786, "ce": 6.459460258483887, "genuineness": 4.319066047668457, "identity": 0.5520095825195312, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e175a227909786afd307588adfa7f185ad6bbd8b0f62e12072b62b4907c6e9a0.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "e186d1070a350afbaaa8582d17e23dc8112902d938828034531eb71d1b26fb35", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6bf43529d7dc2d504e9bb03a76e6bde3d240f302944bc058afe13b094633587d", "generation_seconds_batch": 19.779376802034676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1418747901916504, "target_z": 0.7656249215491181, "ce": 6.078212261199951, "genuineness": 3.9173994064331055, "identity": 0.43535661697387695, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e186d1070a350afbaaa8582d17e23dc8112902d938828034531eb71d1b26fb35.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "e1ffad7574cafc89b66bd1024c51f68a5d29530e90f8da46da5cde946f162ec8", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "57d2165539bced819a7ffc09e993900e7393234145d39c66bdb8575f045a3678", "generation_seconds_batch": 21.586594316991977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3311219215393066, "target_z": 0.972656350610709, "ce": 5.927301406860352, "genuineness": 4.15588903427124, "identity": 0.6368720531463623, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e1ffad7574cafc89b66bd1024c51f68a5d29530e90f8da46da5cde946f162ec8.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "e22a57f5cf9af35f23c69a7e3da4944054a5ce7e844dd587012431fa42c4e1c9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c1ae51d9f1356a2690f79b1fae3e952a0422defc2e957c04d11dc44aea248f9b", "generation_seconds_batch": 15.872544825077057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.641772508621216, "target_z": 1.3124999959246295, "ce": 6.1020402908325195, "genuineness": 3.7165660858154297, "identity": 0.4307325482368469, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e22a57f5cf9af35f23c69a7e3da4944054a5ce7e844dd587012431fa42c4e1c9.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "e284acb9072afe8cd88da155ffb923da736233fa6efe2977024067d4abddfd4e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "385669abb13f381062c7163292f29d184d5eb31c749454fc10809ee4714a0de5", "generation_seconds_batch": 19.779376802034676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.345404624938965, "target_z": 0.988281255858345, "ce": 6.213237762451172, "genuineness": 3.8546390533447266, "identity": 0.3318113088607788, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e284acb9072afe8cd88da155ffb923da736233fa6efe2977024067d4abddfd4e.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "e2a1cd038392b350e27ff020a8b04bdb8e453c578845eb198da112aa9cbe7ebb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9193f4e96b2a1fc74c0adc9e4bb9d21bd7feb356f38685492dcb16aac8bc9b9c", "generation_seconds_batch": 15.428328430978581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 6.268836498260498, "genuineness": 4.105680465698242, "identity": 0.3626915216445923, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e2a1cd038392b350e27ff020a8b04bdb8e453c578845eb198da112aa9cbe7ebb.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "e2c9c0dddb6da201ec6270b9cf2f3039d201c3c0cbd17d4afc094e9ffb11ef67", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6af99db991d59d774eaa4b344e0a3c7fb37eeb3ed7c4611ac9a0da23ab6bd770", "generation_seconds_batch": 20.604531178018078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4418134689331055, "target_z": 1.0937500183391673, "ce": 5.967014789581299, "genuineness": 4.256305694580078, "identity": 0.6308807134628296, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e2c9c0dddb6da201ec6270b9cf2f3039d201c3c0cbd17d4afc094e9ffb11ef67.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "e2d66f2ea2eaf60c7558b32d5f87247c94fe36ba73531f32cd92599eb9268898", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dc54c996f51e3a430796fa4d9701c1e647fd8e43b65e490bbfbca16ddaeaa6b9", "generation_seconds_batch": 21.922677977010608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8203072547912598, "target_z": 1.5078123548149263, "ce": 5.967014789581299, "genuineness": 4.337893962860107, "identity": 0.4604175388813019, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e2d66f2ea2eaf60c7558b32d5f87247c94fe36ba73531f32cd92599eb9268898.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "e3003e7c83c632de005929b5e596a29b8b0d9483990232bd342b26500f6fe1f4", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5ebb2964180b496242a3c241707fe8964c379c51f374deb2391692855b443a55", "generation_seconds_batch": 15.048330485005863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.052607536315918, "target_z": 0.6679688725158253, "ce": 6.1020402908325195, "genuineness": 4.3881025314331055, "identity": 0.6334203481674194, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e3003e7c83c632de005929b5e596a29b8b0d9483990232bd342b26500f6fe1f4.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": "e3222b623a00416436a13d47465faded76fd5a663cad23445f9f5b5b397877d8", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15953bc1ebe9b5085659ede38562686d226eec04354485af089e66440051f6fc", "generation_seconds_batch": 17.033917936962098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5560758113861084, "target_z": 1.2187500427913902, "ce": 6.229123115539551, "genuineness": 4.394378662109375, "identity": 0.6513482928276062, "hypothesis": "De weg gaat linksaf naar de brug, loopt verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e3222b623a00416436a13d47465faded76fd5a663cad23445f9f5b5b397877d8.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "e34e2f31c7a5d178b4b95e81bf2499bc7a739fefdb9ae68fe4e51342deaea1f2", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3d7122155bc78bfb8183472e0bb079465117f56cf080f629d6f54280b7d998d", "generation_seconds_batch": 23.21115234401077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0488319396972656, "target_z": 1.7578124037193723, "ce": 5.927301406860352, "genuineness": 3.7165660858154297, "identity": 0.18694020807743073, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e34e2f31c7a5d178b4b95e81bf2499bc7a739fefdb9ae68fe4e51342deaea1f2.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "e3858f99e5d82453f8cc8ba82f9ecfff93ae7cf3dbf895281b5db59eb6a9c900", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "518072f03968e4c1da6c2faf1e6764d4335c19288906635a7ef507b9710d8601", "generation_seconds_batch": 21.656958049046807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.077397584915161, "target_z": 1.7890624750383557, "ce": 5.673136234283447, "genuineness": 3.722842216491699, "identity": 0.41383492946624756, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e3858f99e5d82453f8cc8ba82f9ecfff93ae7cf3dbf895281b5db59eb6a9c900.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "e38ecde45b2e51d1ce61b17f6b17487b4fdbca5fe6e43600c51ffa1d94f7f662", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d88193c64671a76d51faa8cdc7aa453d89744254422c778849c0979f9b1f83f1", "generation_seconds_batch": 21.360249279998243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.606065511703491, "target_z": 1.273437471981828, "ce": 6.197352409362793, "genuineness": 4.406930446624756, "identity": 0.7284207344055176, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e38ecde45b2e51d1ce61b17f6b17487b4fdbca5fe6e43600c51ffa1d94f7f662.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "e5b8129f28d700b29f8d4b6f355e9cc15d84d18ad149a3542b72dc3219ac7446", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "97b13bd5afe2333429cd6098bec21ef41e26dc56618d4516ac3149dd21039357", "generation_seconds_batch": 21.922677977010608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.541792869567871, "target_z": 1.2031248767200426, "ce": 5.9431867599487305, "genuineness": 4.369274139404297, "identity": 0.5511106252670288, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e5b8129f28d700b29f8d4b6f355e9cc15d84d18ad149a3542b72dc3219ac7446.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "e5c217bfec9b7c0a66b5ffe4120f414f6c8e6290f6600c56f8388811c6f0d36c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "55a79356e54d9b9b4489abfe7cd0f4632449fed3346036545a6491c94dd0c419", "generation_seconds_batch": 20.820797253982164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3989651203155518, "target_z": 1.0468750417725474, "ce": 5.863759994506836, "genuineness": 3.823258876800537, "identity": 0.37654611468315125, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e5c217bfec9b7c0a66b5ffe4120f414f6c8e6290f6600c56f8388811c6f0d36c.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": "e62cfae9303cef290ebe061cf1a561d12589f7f677b0a5bbb8f16f781161b913", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "142062dd329710fa5892b18b2685bd65150d57f53b47eaf08ceaa60b866ccb7f", "generation_seconds_batch": 20.678066977998242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8060245513916016, "target_z": 1.4921874495672902, "ce": 6.0305562019348145, "genuineness": 3.8044304847717285, "identity": 0.5403847098350525, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna, naast het raam, neem ze mee als je weggaat!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e62cfae9303cef290ebe061cf1a561d12589f7f677b0a5bbb8f16f781161b913.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "e659319a6f0471a0c8dcab7a5051c2f89a1777cb22a2f243f6f2f58eff90cded", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "93c591fde63b2c5ed7d9ee6c7b0d8ebe99c6b43e2ed38a59642091c0e61c16b3", "generation_seconds_batch": 15.463947345037013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4918031692504883, "target_z": 1.1484374475296049, "ce": 6.157639026641846, "genuineness": 4.582659721374512, "identity": 0.7918931245803833, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Comme Eno de Stéte et ses ours, les", "wer": 0.4444444444444444, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e659319a6f0471a0c8dcab7a5051c2f89a1777cb22a2f243f6f2f58eff90cded.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": "e6a1d3c1cee10db2165fd50a400b798fd7047992c4a72307b3a4a4d463bbf2ab", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5359c8c39260f741b5689fd37055dd7b4bb70b944ae61533e44508fbcb80dca", "generation_seconds_batch": 21.008579100947827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.648913860321045, "target_z": 1.3203124485484476, "ce": 6.419747352600098, "genuineness": 4.337893962860107, "identity": 0.37516459822654724, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade. Dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e6a1d3c1cee10db2165fd50a400b798fd7047992c4a72307b3a4a4d463bbf2ab.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "e6b1dd85ca2026ee3386e23c08ed5f168539c0f06319823707fd76720a43d73c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "33b7d89154bfb93dbf3a2233d913ebf152175931739a4b624e5452fb4b1cc81e", "generation_seconds_batch": 19.84660206909757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.248995780944824, "target_z": 0.882812493377523, "ce": 6.24500846862793, "genuineness": 3.9173994064331055, "identity": 0.3378216326236725, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e6b1dd85ca2026ee3386e23c08ed5f168539c0f06319823707fd76720a43d73c.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Intense Interest. 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": "930efcedf218be8cdf49a69e616f98291fd87ce07c12af99e25dd37258680abf", "generation_seconds_batch": 17.184532622923143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2775614261627197, "target_z": 0.9140625646965065, "ce": 6.459460258483887, "genuineness": 4.482243061065674, "identity": 0.2785401940345764, "hypothesis": "Someone moved the little blue chair. It used to stand here, beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.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": "e6f42c47fd50e0a4f743bc9434bb57b447aeaeda0e030cb46415a44d54f30578", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b49b6369c9b4b8b480ad148e4b994d47f8eed6f9e861aab1b2d1740af96e2684", "generation_seconds_batch": 16.969005696009845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5132274627685547, "target_z": 1.1718750662247703, "ce": 6.324435234069824, "genuineness": 4.582659721374512, "identity": 0.4731718897819519, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zum kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e6f42c47fd50e0a4f743bc9434bb57b447aeaeda0e030cb46415a44d54f30578.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "e6fad21383a044b2a9818c5d20905bd386a1992d50ff12212c693fd50d6c5d1c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3d3ce582bbaf71abf6159c4dd2442c38c6015af6b37a8b43b36705815cdd5258", "generation_seconds_batch": 15.102092346991412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2132887840270996, "target_z": 0.8437499694347214, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.7256739735603333, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e6fad21383a044b2a9818c5d20905bd386a1992d50ff12212c693fd50d6c5d1c.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "e8e465fce30bca9db1269abbb38abc875065f02f5281517a42b53da82169c34a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "13b03f4368e375c6f311ebd0ccb15ceedb0712e0794542c61294b1a8e195697b", "generation_seconds_batch": 22.02536857605446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.598719596862793, "target_z": 2.3593751681090325, "ce": 6.086154937744141, "genuineness": 4.432034492492676, "identity": 0.5957224369049072, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e8e465fce30bca9db1269abbb38abc875065f02f5281517a42b53da82169c34a.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": "e911c8aad4220769874540c23e6753f15f67485b0334df3d78fe0d437c850bee", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4e6e895a0a64e62752976ba25ae245fff279ef45f141b63014a2473729bc781", "generation_seconds_batch": 17.303050674963742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8597897291183472, "target_z": 0.4570312171423254, "ce": 5.990842819213867, "genuineness": 4.632867813110352, "identity": 0.4980752766132355, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e911c8aad4220769874540c23e6753f15f67485b0334df3d78fe0d437c850bee.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "e9192e7f244c9d760d7703dc9631ad7a213e2b9c5044bc96ddc2e65c263d169c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "83803123124fd7c5ee1aa7e9e6e4a72c9cf0c775acf276dc56817739d7f56996", "generation_seconds_batch": 22.51609367900528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.352545976638794, "target_z": 0.9960937084821632, "ce": 6.213237762451172, "genuineness": 4.15588903427124, "identity": 0.2735702395439148, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e9192e7f244c9d760d7703dc9631ad7a213e2b9c5044bc96ddc2e65c263d169c.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "e9639dd766ba576d39858011732ac66fd59ae96d8173afd261b105c49c41ede9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "14b9260df30c614aaaec5a3d12d7614acdc05971e93d1bfb72729ce219455578", "generation_seconds_batch": 19.938471393077634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4989447593688965, "target_z": 1.1562501609771343, "ce": 6.078212261199951, "genuineness": 4.2751336097717285, "identity": 0.538720428943634, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e9639dd766ba576d39858011732ac66fd59ae96d8173afd261b105c49c41ede9.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": "e982ca475e8eb4d8be57fd4fdee8c44cbb665abdde2847d83a97ed6d16f8a565", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I wrote the number on the envelope.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71130bb4778c7cd5ceca87db2858d96c2f4741c877bcc590c1cb0a8997676403", "generation_seconds_batch": 20.875255957012996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.102597236633301, "target_z": 0.722656301706263, "ce": 6.419747352600098, "genuineness": 3.747946262359619, "identity": 0.4062861204147339, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e982ca475e8eb4d8be57fd4fdee8c44cbb665abdde2847d83a97ed6d16f8a565.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "e99e78ef144cd6f6f00775d6733fa0e29dcd7adfaa87e0047524f0a28c4b4077", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5e6d0b98b8b36ca649d2a15b901646902972043f85896805a5a0101cbad3ff75", "generation_seconds_batch": 19.77140656101983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.184518575668335, "target_z": 1.9062500468667607, "ce": 6.395919322967529, "genuineness": 4.444586753845215, "identity": 0.6217762231826782, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e99e78ef144cd6f6f00775d6733fa0e29dcd7adfaa87e0047524f0a28c4b4077.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "e9a0e6756eca9db5a303f34323c7753a67c99c4ed0febab471519ed8513a6287", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9db92e980c8d15a6a3424703b03373b7781d09a8d1e5ad5584a624511a183e11", "generation_seconds_batch": 20.233025470981374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2273669242858887, "target_z": 1.9531250234333803, "ce": 5.982900142669678, "genuineness": 4.507347106933594, "identity": 0.5629251003265381, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e9a0e6756eca9db5a303f34323c7753a67c99c4ed0febab471519ed8513a6287.mp3" }, { "id": "heldout-de-3", "language": "de", "sentences": [ "Jemand hat den kleinen blauen Stuhl umgestellt.", "Er stand hier... neben dem hohen Bücherregal.", "Wir stellen ihn nach dem Essen zurück." ], "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-3", "key": "e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Intense Interest. 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": "34a8edc0c976a1b351c398097acfd00e5e53830dcd409648cf18fb354108c591", "generation_seconds_batch": 15.50372493697796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.288273334503174, "target_z": 0.9257811132203779, "ce": 6.507116317749023, "genuineness": 4.482243061065674, "identity": 0.5716643929481506, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "ea105844f927adf16f48177f59ed70f0f2756895e7746682ed59d6ccace2de45", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dca37146bec7fb3c11c2eef26ab8d0209a797672fe1ebe9bd393cdd277c9d9bb", "generation_seconds_batch": 15.987734155962244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0204710960388184, "target_z": 0.632812444473077, "ce": 6.062326908111572, "genuineness": 4.419482707977295, "identity": 0.726118803024292, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ea105844f927adf16f48177f59ed70f0f2756895e7746682ed59d6ccace2de45.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "ead961278c1f8b040c54b5c8a231004396f4278213b71d363f13808ad0a2a549", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "947d1814a25751336c72513f12f9607a8cd7dd4ee416d084ba3767fd63cd49df", "generation_seconds_batch": 22.19759489397984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1990060806274414, "target_z": 0.8281250641870852, "ce": 6.372091293334961, "genuineness": 4.218649387359619, "identity": 0.4279370903968811, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ead961278c1f8b040c54b5c8a231004396f4278213b71d363f13808ad0a2a549.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "eaf30b83d85b93631deb4e3b3f38a0d4b46df4d028020a46a3adfabe73143c82", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3ca8459a4c299775bf2a3ce55be0deeabd8ed021283fe57559eae64dc7cfa219", "generation_seconds_batch": 20.7917255529901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.784600257873535, "target_z": 1.4687498308721247, "ce": 6.260893821716309, "genuineness": 4.331617832183838, "identity": 0.6571599245071411, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/eaf30b83d85b93631deb4e3b3f38a0d4b46df4d028020a46a3adfabe73143c82.mp3" }, { "id": "heldout-fr-2", "language": "fr", "sentences": [ "La route tourne à gauche après le pont.", "Continue... jusqu’à la petite barrière en bois.", "Je t’attendrai de l’autre côté." ], "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-2", "key": "ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Intense Interest. 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": "cbb84613dbc5263592dd147b8cf575ac565661d78735ee70157d4229a9544258", "generation_seconds_batch": 16.694984839065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6035921573638916, "target_z": 0.17675775130576502, "ce": 6.252951145172119, "genuineness": 4.570107460021973, "identity": 0.8612117767333984, "hypothesis": "La route tourne à gauche après le pont. Continue, jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.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": "ec4c6c42e6adac67ce4be093226301904b5553522f5a4592be2dfed4d5b60f4b", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4465525b85ec2f89740127fca795fb2c654f133a8f633a816b6819f7bb9b7959", "generation_seconds_batch": 15.350442867027596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3703994750976562, "target_z": 1.015624970453564, "ce": 6.38797664642334, "genuineness": 4.394378662109375, "identity": 0.4659666419029236, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ec4c6c42e6adac67ce4be093226301904b5553522f5a4592be2dfed4d5b60f4b.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": "ec5d64de29d0668061a821c430abb258cd4e11ebe6fb857863ae608e1b7debd2", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "258261daef0e52af65be7badbfeaba1bb302806d7e8349e364ccbcef52ad0f36", "generation_seconds_batch": 15.469603147008456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7917418479919434, "target_z": 1.4765625443196542, "ce": 5.927301406860352, "genuineness": 4.218649387359619, "identity": 0.09169130027294159, "hypothesis": "De sleutels liggen op de keukentafel. Ik kijk in de laat en daarnaast het raam. Neem ze mee als je weggaat.", "wer": 0.18181818181818182, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ec5d64de29d0668061a821c430abb258cd4e11ebe6fb857863ae608e1b7debd2.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "ec722f10d8ac4340b162f45b163036f71fd25407e2b939c04e65724ceba9560c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "373adacd90061955b9167c3868571e8747ddbb2df316628b948b088fed6d55f9", "generation_seconds_batch": 21.64453279110603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3918237686157227, "target_z": 1.0390625891487295, "ce": 5.959072113037109, "genuineness": 3.8044304847717285, "identity": 0.4392755627632141, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ec722f10d8ac4340b162f45b163036f71fd25407e2b939c04e65724ceba9560c.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "ec8c8aeae958195a9ce703f8371d634c489de130a89b301eadd56adc8a750c11", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8e3aa30ffcd317e7d7dddd9eb8dcf61926ee2ac2ab4e2ac03902ad96913a5f12", "generation_seconds_batch": 17.7545624289196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9202868938446045, "target_z": 1.6171874740195131, "ce": 6.3641486167907715, "genuineness": 4.482243061065674, "identity": 0.42440879344940186, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ec8c8aeae958195a9ce703f8371d634c489de130a89b301eadd56adc8a750c11.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "ecc83493258acea62028b32f84f32865cf8889cb1bc4802743ee11511fa65868", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c7341568835be2e79da58fa3fd83601c42bc548be50c619e978ec2ddeae05755", "generation_seconds_batch": 22.002744075027294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2061474323272705, "target_z": 0.8359375168109032, "ce": 6.070269584655762, "genuineness": 3.6914620399475098, "identity": 0.27025678753852844, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ecc83493258acea62028b32f84f32865cf8889cb1bc4802743ee11511fa65868.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "edeacc0811f8811c41ebb3a1d750b2f4783fb72926e2816ce6c29c684d0bed04", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8e006a62cb016f568a535d08d40d0e2bdb4b2e5fb2bb84fdc5ac517a9c4c2502", "generation_seconds_batch": 22.260196185903624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1702356338500977, "target_z": 1.8906248807954131, "ce": 6.356205940246582, "genuineness": 4.344170093536377, "identity": 0.5033410787582397, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/edeacc0811f8811c41ebb3a1d750b2f4783fb72926e2816ce6c29c684d0bed04.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "ee35c6d382470756d4e6d2ca500a3ecdac2f4f5da4f080636ce94e1872031979", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a1e66e0fafd786c2780b91bcb332115c4f1e689ac79026d9c0c33fa2d144cbd9", "generation_seconds_batch": 20.902788411010988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.298780918121338, "target_z": 2.0312500713189836, "ce": 5.974957466125488, "genuineness": 3.9676074981689453, "identity": -0.043864116072654724, "hypothesis": "Kijk, ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ee35c6d382470756d4e6d2ca500a3ecdac2f4f5da4f080636ce94e1872031979.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": "ee443129775e622afafb48a2cfdcbb6695f28fb14c40bda165dffd27ddbe6cac", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa2db2224f0aa2af9dc269ec7b3d550fddc319cafb893eb4116073f0da811542", "generation_seconds_batch": 20.604242734028958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0274078845977783, "target_z": 1.734375045847918, "ce": 6.292664527893066, "genuineness": 3.9927117824554443, "identity": 0.6304888725280762, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ee443129775e622afafb48a2cfdcbb6695f28fb14c40bda165dffd27ddbe6cac.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "eec13d7eb53ed8ef502757d8f5f9a00fa889cae904d030f2a24b68015cfe8e83", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6527b8a151fe73223538b219f07c8dd17fa31f7590d0160666207ff2e80081a4", "generation_seconds_batch": 21.254621229949407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1059632301330566, "target_z": 1.8203125463573393, "ce": 6.316492557525635, "genuineness": 4.344170093536377, "identity": 0.23189020156860352, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/eec13d7eb53ed8ef502757d8f5f9a00fa889cae904d030f2a24b68015cfe8e83.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "eff632e552807f84ff4fbd09a898922ea8d783c44f5a1c5c5ada4c011d16bbb7", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f110d29c6c7842f86caedf39426877165fcc97583e0c978249f4f7739ae9b8d9", "generation_seconds_batch": 19.747626291005872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3846821784973145, "target_z": 1.0312498757012, "ce": 6.205295085906982, "genuineness": 4.344170093536377, "identity": 0.7797616720199585, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/eff632e552807f84ff4fbd09a898922ea8d783c44f5a1c5c5ada4c011d16bbb7.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": "f089de3afe51e112061b9258976cbb380faba9c6c0965568c86a63987b0ec063", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93888e2f84df447f7433891ffdd8c7b2f071049215bdc06a593f1ab96928003e", "generation_seconds_batch": 15.472160795005038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.541792869567871, "target_z": 1.2031248767200426, "ce": 6.165581703186035, "genuineness": 4.482243061065674, "identity": 0.6377284526824951, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f089de3afe51e112061b9258976cbb380faba9c6c0965568c86a63987b0ec063.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "f0fce5cd43a86e312c05b9203de2c0fe97350be8b68faf779ab75d3dc2a69806", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8afd94ad0b1b128a980a18584d07fe034b1fdeac6885ed5a0429e06e6ce1aa9c", "generation_seconds_batch": 20.18271615996491, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7274692058563232, "target_z": 1.4062499490578688, "ce": 5.998785495758057, "genuineness": 3.7667744159698486, "identity": 0.2827456295490265, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f0fce5cd43a86e312c05b9203de2c0fe97350be8b68faf779ab75d3dc2a69806.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "f10ce870e12ed65fa5d406a9be0b1f0c2197c797d58a4ec77c10d08523dd5f4a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "083e31158b5e134ad58176c42cb8d3bf11118a42221827c116d5c09be2f9439e", "generation_seconds_batch": 23.45117224403657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9919055700302124, "target_z": 0.6015625035659492, "ce": 6.205295085906982, "genuineness": 4.3504462242126465, "identity": 0.7121195793151855, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f10ce870e12ed65fa5d406a9be0b1f0c2197c797d58a4ec77c10d08523dd5f4a.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": "f13b5dac6da791e95811aba3a8ae58a6b988592ee20dd347074ba31848ca2154", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3323bcb89ad3dda0acd5da5fa636168b13b975c94088923b0d5e3a6330ebd789", "generation_seconds_batch": 15.854753119056113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9917008876800537, "target_z": 1.6953125219051164, "ce": 6.062326908111572, "genuineness": 3.8295347690582275, "identity": 0.7343292236328125, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f13b5dac6da791e95811aba3a8ae58a6b988592ee20dd347074ba31848ca2154.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": "f19a89e127dd5d1bd2d63a678eb64deb070eeb506571325ff80a3a192b25fb5f", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "98df19a8d67001eadc604f3f0c468a17de716c9db3ca56c9701fc5ccd44a18d2", "generation_seconds_batch": 16.96798999106977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6846208572387695, "target_z": 1.3593749724912492, "ce": 6.23706579208374, "genuineness": 4.243753433227539, "identity": 0.4898546040058136, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana llévatelas cuando te vayas.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f19a89e127dd5d1bd2d63a678eb64deb070eeb506571325ff80a3a192b25fb5f.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "f1c00e00eb98dd72791cb89ac0151e4bf675940e8a73efa394923aec362ac6b5", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8aefe51ccd35e3f98476af7ead850d6cfc543065cbac9d32355c44142cf915a4", "generation_seconds_batch": 22.23865743004717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4560961723327637, "target_z": 1.1093749235868033, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.704150378704071, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f1c00e00eb98dd72791cb89ac0151e4bf675940e8a73efa394923aec362ac6b5.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "f1e88d13ce4b0984248946c0a3598acd913f0096a69bc421fe102eed2d76538b", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "42fff8fba2d93ad9f3e600d8d23cb6d2ebd7b257aa818690522ce4550943211b", "generation_seconds_batch": 15.921878305030987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.049036741256714, "target_z": 0.6640625157920607, "ce": 6.197352409362793, "genuineness": 4.256305694580078, "identity": 0.3972494602203369, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f1e88d13ce4b0984248946c0a3598acd913f0096a69bc421fe102eed2d76538b.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Intense Interest. 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": "73105d7e05a1f0fce9715d7c897d4b5de356267bd000360838729d1bfbd34275", "generation_seconds_batch": 16.94332864799071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.913350224494934, "target_z": 0.5156250030565279, "ce": 6.2767791748046875, "genuineness": 4.406930446624756, "identity": 0.6146126389503479, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "f2ac48e3ee24afcb1f7d957597e7ffcd7bcab06506c9372be9f354e04605d3d3", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7884b8d251e0d5685aaa2863989fc9974c0fd20c57d91b6eabee6b7ba5827a5b", "generation_seconds_batch": 14.883428246015683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6989035606384277, "target_z": 1.3749998777388854, "ce": 6.260893821716309, "genuineness": 3.835810661315918, "identity": 0.6717430353164673, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f2ac48e3ee24afcb1f7d957597e7ffcd7bcab06506c9372be9f354e04605d3d3.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "f2ba7db30cd542bf77a1f896c4cea883d08b5e48407e6f30a8fd5348c0ee9419", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cd67d8fcfc4c89388cd69788b0356c5acd02331a0c0d2f085621fe2f632839ac", "generation_seconds_batch": 20.563803842058405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2345082759857178, "target_z": 1.9609374760571985, "ce": 6.006728172302246, "genuineness": 4.20609712600708, "identity": 0.2904178202152252, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f2ba7db30cd542bf77a1f896c4cea883d08b5e48407e6f30a8fd5348c0ee9419.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "f30e7c64c30529cf033e1f351b5f8040230ab9ded89c49b994e584f7c0cc0e21", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cdc3a7d1d2fbfa1630a5c3d41aecde0cf151f3c7a856fe049dff112779c3fdd2", "generation_seconds_batch": 20.135228391969576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.255932331085205, "target_z": 1.9843748339286527, "ce": 6.252951145172119, "genuineness": 4.306513786315918, "identity": 0.6326572299003601, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f30e7c64c30529cf033e1f351b5f8040230ab9ded89c49b994e584f7c0cc0e21.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "f3ae4b3ea6ad7a10a5df54f463e5bad122cbaab72c5d289c49d5ca3c8217dd73", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "07d6321501fcdebb72e260237a4913f6dcb91d604ff62d06c50cec1d3c72dfc5", "generation_seconds_batch": 20.288220369024202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.052607536315918, "target_z": 0.6679688725158253, "ce": 5.990842819213867, "genuineness": 4.331617832183838, "identity": 0.5385961532592773, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f3ae4b3ea6ad7a10a5df54f463e5bad122cbaab72c5d289c49d5ca3c8217dd73.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "f3b1711d6d16920b347499e4e186d9732542229ec34c5688ffc863a04592f810", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cfcdb9061336b03ffbfe27f3cb399043a7e2a89c4f82fafa237b03eb371b9853", "generation_seconds_batch": 21.08184513496235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.352545976638794, "target_z": 0.9960937084821632, "ce": 6.221180438995361, "genuineness": 4.243753433227539, "identity": 0.6855025291442871, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f3b1711d6d16920b347499e4e186d9732542229ec34c5688ffc863a04592f810.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "f3d5335fdefe3387106c3ab3e66fcfe18a349c4d6dfcb6d37e54a0d63b07ec0c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "efa7c812c10d5ab8e2b03a7afd585135abe7fe36c8edc757199cc541de5d9d85", "generation_seconds_batch": 21.96642640104983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7417521476745605, "target_z": 1.4218751151292164, "ce": 5.77639102935791, "genuineness": 3.9425034523010254, "identity": 0.14328192174434662, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f3d5335fdefe3387106c3ab3e66fcfe18a349c4d6dfcb6d37e54a0d63b07ec0c.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "f41fda1bb78c0c5ea2066eb51c088246b444423ca537f30116b062ae8c721545", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3e0f4e5b71e05608281a54d54033476a88fc4f46300ccf1f8f949ae7e658e382", "generation_seconds_batch": 21.157516070990823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6415677070617676, "target_z": 2.4062498838519413, "ce": 6.300607204437256, "genuineness": 4.231201171875, "identity": 0.5289331078529358, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f41fda1bb78c0c5ea2066eb51c088246b444423ca537f30116b062ae8c721545.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "f45da1686cfb7ebe2dea3cdbc832721a4223ea01cfd57cded0a6093071e7c5a9", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ec1e9753012fb5495e5c75aba7c0bb7fc99e86c04acc7ac42ae103ddbbb2daea", "generation_seconds_batch": 15.30385332996957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8401509523391724, "target_z": 0.43554690722089795, "ce": 6.086154937744141, "genuineness": 4.419482707977295, "identity": 0.6745340824127197, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f45da1686cfb7ebe2dea3cdbc832721a4223ea01cfd57cded0a6093071e7c5a9.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": "f45e5f7d451d6d0aa0ef673c2dea7a96f3f2b4f307fa76f14d69420ccbdfad2e", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af20f596e7853a5b393a84a143505effa1819bcfa647fdbbffa2efe455ef8d7c", "generation_seconds_batch": 16.230300738010556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.934569835662842, "target_z": 1.6328126400908605, "ce": 6.086154937744141, "genuineness": 4.400654315948486, "identity": 0.11614619195461273, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f45e5f7d451d6d0aa0ef673c2dea7a96f3f2b4f307fa76f14d69420ccbdfad2e.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "f479d6ee0446567d006b3ddd97e1c653b1f91e6a33c71614a8d643c50c57619f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be9c032d9b459cf2239162e265bb090544782008be679dd746754cd7c85a9708", "generation_seconds_batch": 21.18491195095703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4130430221557617, "target_z": 2.156249834947495, "ce": 6.09409761428833, "genuineness": 4.055472373962402, "identity": 0.6434838175773621, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f479d6ee0446567d006b3ddd97e1c653b1f91e6a33c71614a8d643c50c57619f.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "f4b24ecd5ddfb78f84ae8f287c65b26766b5bf147780064809b526277edde44a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3a6ad7aa8389b1a9886adb80e6cace1837aaa63b68092e7c534154acde266036", "generation_seconds_batch": 23.319186892011203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3346924781799316, "target_z": 0.9765624465107623, "ce": 6.340320587158203, "genuineness": 4.425758361816406, "identity": 0.3113083839416504, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f4b24ecd5ddfb78f84ae8f287c65b26766b5bf147780064809b526277edde44a.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "f5efd730790ae226836a1058dae1f178ab988acc49db1bcd5bd9b03ca5fc3469", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e7b63e00639edb7237ce733f85cb7af6cd46e20114272833965aebe11ce44b91", "generation_seconds_batch": 21.003292822977528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0740315914154053, "target_z": 0.6914062303872796, "ce": 6.165581703186035, "genuineness": 4.482243061065674, "identity": 0.6431347131729126, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f5efd730790ae226836a1058dae1f178ab988acc49db1bcd5bd9b03ca5fc3469.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": "f6050d4621218a92cc878bb177784ffa4f5717c2eeb492e961e6e14dade26a69", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b2297e6fd4b39ba71471014e08a6a0747d4762e1a0ed8a84843eee3a981eaf4", "generation_seconds_batch": 17.334229354048148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3273463249206543, "target_z": 2.0624998818142557, "ce": 6.1020402908325195, "genuineness": 4.319066047668457, "identity": 0.6471250653266907, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue, elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f6050d4621218a92cc878bb177784ffa4f5717c2eeb492e961e6e14dade26a69.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "f6627a7e1d84b2f6ff0bc07265e7f2f053d7191b001580d42839947381e5d90e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c7fd9d0c104db0f4bdcf833c0d7a46602ea7b1302fa9866c78a17a7af7e7712c", "generation_seconds_batch": 19.731795337051153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.055973529815674, "target_z": 1.7656251171669015, "ce": 6.006728172302246, "genuineness": 4.105680465698242, "identity": 0.31662070751190186, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f6627a7e1d84b2f6ff0bc07265e7f2f053d7191b001580d42839947381e5d90e.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "f69705fc9bba71ba25cb93b707f2f07382a471030bc1f285078113ed25d62f3f", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f1e3a981a5a39233b56f9e77b1a915cb49c060d440598eec8b0e95847022475f", "generation_seconds_batch": 20.96784788405057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245425224304199, "target_z": 0.8789063974774696, "ce": 6.0305562019348145, "genuineness": 4.143336772918701, "identity": 0.5065816640853882, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f69705fc9bba71ba25cb93b707f2f07382a471030bc1f285078113ed25d62f3f.mp3" }, { "id": "emo_Interest-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-0", "key": "f710c68a82a6e12e8558fdafdfaf6758fbc17fe1cfb185fc382fd3860f52812b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] The door is still open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c24fb67a366c57893aa32ad071682469b3e19111c62a76e5b41801ae31017d98", "generation_seconds_batch": 22.431671927915886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.534651756286621, "target_z": 1.195312684919936, "ce": 5.903473377227783, "genuineness": 3.5188708305358887, "identity": 0.2577921152114868, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f710c68a82a6e12e8558fdafdfaf6758fbc17fe1cfb185fc382fd3860f52812b.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "f7314ea97a4159a4a3dbb3ede8c90983cf2f5c1810a4bc25c54396fcb24a80fe", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f728455041653c393e14797deb27d1bf8c18d51d6c18a3268673eba4404c17ce", "generation_seconds_batch": 23.13724829000421, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.163299083709717, "target_z": 0.7890625402442836, "ce": 6.427689552307129, "genuineness": 4.394378662109375, "identity": 0.6324621438980103, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f7314ea97a4159a4a3dbb3ede8c90983cf2f5c1810a4bc25c54396fcb24a80fe.mp3" }, { "id": "heldout-fr-1", "language": "fr", "sentences": [ "Les clés sont sur la table de la cuisine.", "J’ai regardé dans le tiroir... puis près de la fenêtre.", "Prends-les quand tu partiras." ], "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-1", "key": "f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Intense Interest. 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": "3333080b21bd2ddb82d05eb06620f3c831b91433ae7fba978b1fa2e466b0c5fe", "generation_seconds_batch": 19.516648349002935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3061270713806152, "target_z": 0.9453126360154901, "ce": 6.133810997009277, "genuineness": 4.482243061065674, "identity": 0.696718692779541, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis, près de la fenêtre, prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Interest-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-1", "key": "f825c90f859dc62a9bc3398e01d4bd98cc6c3788573ba26eee50a4c0cbf417a1", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] He encontrado la cajita.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "62022df77d91f925ccf4210da7fd0ebc9f04d4c5fe179b3fbfb226933b143e9e", "generation_seconds_batch": 22.319253675057553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.598719596862793, "target_z": 2.3593751681090325, "ce": 5.692992687225342, "genuineness": 4.055472373962402, "identity": 0.4162611663341522, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f825c90f859dc62a9bc3398e01d4bd98cc6c3788573ba26eee50a4c0cbf417a1.mp3" }, { "id": "emo_Interest-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-0", "key": "f8381da1ccf73a241a00ebb0904070af8b8d38cf5c48ebcc93fdc66f09624568", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La porte est encore ouverte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "398e71061430db23066853cfd73d689b2e7ec080303a0984eba2c6d694b12d0a", "generation_seconds_batch": 21.00411892007105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.527510166168213, "target_z": 1.1874999714724066, "ce": 5.879645347595215, "genuineness": 4.074300289154053, "identity": 0.537404477596283, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f8381da1ccf73a241a00ebb0904070af8b8d38cf5c48ebcc93fdc66f09624568.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d", "bucket": "emo_Interest", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Intense Interest. 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": "029d85f459a6f1836aa1295f6638f501dad28cf04d66f7cbb0167aeab78f0a0c", "generation_seconds_batch": 15.63570584799163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.163299083709717, "target_z": 0.7890625402442836, "ce": 6.268836498260498, "genuineness": 4.193545341491699, "identity": 0.6000354886054993, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "f88cd8895a0cfc257919aa99382fd12ff7940d2e7cf3408f4369d673b60e4c94", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f44dff3056e3eaf058fe4873fe9fadd7d3e5d148f4b030a64429330037dbdad4", "generation_seconds_batch": 20.321611452964135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.245425224304199, "target_z": 0.8789063974774696, "ce": 6.022613525390625, "genuineness": 4.080576419830322, "identity": 0.3550482392311096, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f88cd8895a0cfc257919aa99382fd12ff7940d2e7cf3408f4369d673b60e4c94.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": "f8aba936d0e0e2ddc00833a8499fd3ccfc9a271315d63353b914f11fdb6314d3", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Someone moved the little blue chair.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "126c478518033e7f0f21aaa0bc77a9610dc439767136535f15a3b1939558a713", "generation_seconds_batch": 21.085157086024992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5632171630859375, "target_z": 1.2265624954152081, "ce": 6.38003396987915, "genuineness": 4.281409740447998, "identity": 0.41626495122909546, "hypothesis": "Someone moved the little blue chair. It used to stand here, beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f8aba936d0e0e2ddc00833a8499fd3ccfc9a271315d63353b914f11fdb6314d3.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "f9137d31b251f811bbc1366a5ee7a1fc5a2e07eefc0b0fc5f8762cb28664bcbb", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "45838d0ab2cd1a57dfc67014390991a9bd1ae1a6502653720c84bd29c9230124", "generation_seconds_batch": 19.83091966493521, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3989651203155518, "target_z": 1.0468750417725474, "ce": 5.816103935241699, "genuineness": 3.562803030014038, "identity": 0.3844611346721649, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f9137d31b251f811bbc1366a5ee7a1fc5a2e07eefc0b0fc5f8762cb28664bcbb.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "f91a81945a913e5ea80c60100e2f75900ccaa561320b475a2626aebc98b25a7a", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "548355dd26b577ce8ae4723b9d3844fde178c6d4b6c82a0356fe804878292cf8", "generation_seconds_batch": 20.611205457011238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.191659927368164, "target_z": 1.9140624994905786, "ce": 6.229123115539551, "genuineness": 4.256305694580078, "identity": 0.39539986848831177, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f91a81945a913e5ea80c60100e2f75900ccaa561320b475a2626aebc98b25a7a.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": "f94cabba0fa1e7be780b9037ed9b6a548a2f16e2d1596b437a152c1ce64aa474", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ccd6dd0713f3a4d3e3244d5619dc9280e58fcfe58b471e4655d473225739615", "generation_seconds_batch": 15.338630032958463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7917418479919434, "target_z": 1.4765625443196542, "ce": 6.213237762451172, "genuineness": 4.607763767242432, "identity": 0.8021541833877563, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f94cabba0fa1e7be780b9037ed9b6a548a2f16e2d1596b437a152c1ce64aa474.mp3" }, { "id": "emo_Interest-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-en-1", "key": "f95b6fb3d775d3e0e22b9c0a9cb6b79b8c8d98a7896e54269e7c14b2b3c0d3dc", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] I found the little box.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "370e319aed982428f29b93aeff5c33d42103859937a7061a6c0f6a0df06a3640", "generation_seconds_batch": 15.242760193999857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.055973529815674, "target_z": 1.7656251171669015, "ce": 6.356205940246582, "genuineness": 4.494794845581055, "identity": 0.4924044609069824, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f95b6fb3d775d3e0e22b9c0a9cb6b79b8c8d98a7896e54269e7c14b2b3c0d3dc.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "f98a990959412ac7c791d5a6ad1d4f29cb5aac87497db7f3198d9e1de314bd65", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "26de716d1956d149bc38a879dc69948fa81e7d12d728394c7a34e7fa2e93c8d6", "generation_seconds_batch": 21.802072854014114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.420389175415039, "target_z": 1.0703123996440018, "ce": 6.117925643920898, "genuineness": 3.961331605911255, "identity": 0.3345220685005188, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinkommen.", "wer": 0.125, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f98a990959412ac7c791d5a6ad1d4f29cb5aac87497db7f3198d9e1de314bd65.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "f9aa3bcb6abe45fb785090b74b084cedf9cbd89c29f787d38f179cef311f7a61", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ce1d6b8cc54567a6ece858f28fa49a2393a7ccbe618085e1a0149a0d08a91394", "generation_seconds_batch": 20.321611452964135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3846821784973145, "target_z": 1.0312498757012, "ce": 6.252951145172119, "genuineness": 4.2751336097717285, "identity": 0.5055477023124695, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/f9aa3bcb6abe45fb785090b74b084cedf9cbd89c29f787d38f179cef311f7a61.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "fa1d554238878d677becfffe0758263a47b77982c8d2b51a58acabaed2afe108", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8fa5b8809b685c1b35dc39fa090c1e41f6e86fe305a1dd03191c0e09d74eb0a8", "generation_seconds_batch": 20.92242829303723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6346311569213867, "target_z": 1.3046875433008114, "ce": 6.1894097328186035, "genuineness": 4.362998008728027, "identity": 0.22224435210227966, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fa1d554238878d677becfffe0758263a47b77982c8d2b51a58acabaed2afe108.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "fa7279c5f7e4ba3cc9d00b01e40c801090cc3c1cb07b49f0261c3cb960ae4f51", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8a8ba28ffba553d65fda4cd26133e5c3f957a8b099e73863995080be11926526", "generation_seconds_batch": 19.771799605921842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2204301357269287, "target_z": 0.8515624220585394, "ce": 5.831989288330078, "genuineness": 4.099404335021973, "identity": 0.6727125644683838, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fa7279c5f7e4ba3cc9d00b01e40c801090cc3c1cb07b49f0261c3cb960ae4f51.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": "fa89526a8009b945ef00fe2499f8f2e5038b3ae4a1ec8bc0583e0999767b636a", "bucket": "emo_Interest", "phase": "heldout", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Your message arrived after I had left.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fc0738bf51fe820811afbceb33786f22928b75bdf66086cf74a81bbdf1a2293a", "generation_seconds_batch": 15.51565354410559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0276126861572266, "target_z": 0.6406251579206065, "ce": 6.316492557525635, "genuineness": 3.9550557136535645, "identity": 0.5378989577293396, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fa89526a8009b945ef00fe2499f8f2e5038b3ae4a1ec8bc0583e0999767b636a.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "fb7064df97e57ecb8d819ec4a9db2ec7f07ccdc8ca48e4a4a26f525593876977", "bucket": "emo_Interest", "phase": "wording", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0ebc17d97b43ac29c6175f3c383185593e5d4608fcab0731aaad38e82323099b", "generation_seconds_batch": 15.77211151807569, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.241854429244995, "target_z": 0.8750000407537049, "ce": 5.903473377227783, "genuineness": 3.961331605911255, "identity": 0.4613948464393616, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fb7064df97e57ecb8d819ec4a9db2ec7f07ccdc8ca48e4a4a26f525593876977.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "fbada85fc978398e253190bfc471f213f7a439d4fda636d0d84ec98c6afe5977", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7da28adb3508975d26507bbb2a4d36d7535cec4358f989ec27fb100466998c1d", "generation_seconds_batch": 19.268706541042775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1702356338500977, "target_z": 1.8906248807954131, "ce": 5.486483573913574, "genuineness": 3.7667744159698486, "identity": 0.4253016710281372, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fbada85fc978398e253190bfc471f213f7a439d4fda636d0d84ec98c6afe5977.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "fc45a0b3a437978b1a4129499706caa4b6ecc954af4e31d8d91aa4ea0f959316", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "45dcfea315a0a3ae09da732262bda5c7d2feae22a8ad473c7e6700a7c964ff49", "generation_seconds_batch": 14.769277616986074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0988216400146484, "target_z": 1.8124998329098099, "ce": 5.804190158843994, "genuineness": 3.9173994064331055, "identity": 0.3208015561103821, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fc45a0b3a437978b1a4129499706caa4b6ecc954af4e31d8d91aa4ea0f959316.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "fc5fb510a97fb57ff4107098c410915c15957c2e98f82c53ea0f0921ecd1e966", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b748cb10a568df4a35e1b24de7b962375f7f9c2c5ec361b52107d615e73707aa", "generation_seconds_batch": 23.177062809932977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.541588306427002, "target_z": 2.2968750254710657, "ce": 5.569881439208984, "genuineness": 4.105680465698242, "identity": 0.35685107111930847, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fc5fb510a97fb57ff4107098c410915c15957c2e98f82c53ea0f0921ecd1e966.mp3" }, { "id": "emo_Interest-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-0", "key": "fd0e8164f4d40c900b738e8d0271d72dd952723efb2827fa8d1df17a4734dbe6", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] De deur staat nog open.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cf2c9577804ba24c4f4fbc96c2204017f6b3b4c9607fd04f88e013b30034c7ab", "generation_seconds_batch": 22.563913080957718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4918031692504883, "target_z": 1.1484374475296049, "ce": 6.24500846862793, "genuineness": 4.080576419830322, "identity": 0.47809112071990967, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fd0e8164f4d40c900b738e8d0271d72dd952723efb2827fa8d1df17a4734dbe6.mp3" }, { "id": "emo_Interest-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-es-0", "key": "fd23e3b5a0a350068a23e8b22288737cd8b543b175f41f70c57639545fa1f40b", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] La puerta sigue abierta.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6635cc287f877fb3b02bdf0e025f62374a4397a5565c2422ec212a6cd9236398", "generation_seconds_batch": 22.543488178984262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.598924160003662, "target_z": 1.2656250193580099, "ce": 5.387199878692627, "genuineness": 3.835810661315918, "identity": 0.661186933517456, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fd23e3b5a0a350068a23e8b22288737cd8b543b175f41f70c57639545fa1f40b.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "fdd840a2ef96f4d24ef542cf66917de674de31793c7e4d72abf4692e0ba47489", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a83289b8e461454c46c9589e0a1f443318193ab44de7f5c18675200da065691", "generation_seconds_batch": 22.57390055700671, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.063114643096924, "target_z": 1.7734373089670084, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.6761526465415955, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fdd840a2ef96f4d24ef542cf66917de674de31793c7e4d72abf4692e0ba47489.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "fde74be6181ef32dc61eda7f6413c134f4d2cd0cd653bd7eb9a2edf772cf003e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3924b7fbf0df3fc0ae1e23d66bd2762bcfdc6e9d2ddbdd153da5beff7609165a", "generation_seconds_batch": 20.137151267030276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6703381538391113, "target_z": 1.3437500672436131, "ce": 6.1020402908325195, "genuineness": 3.936227321624756, "identity": 0.5755870938301086, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fde74be6181ef32dc61eda7f6413c134f4d2cd0cd653bd7eb9a2edf772cf003e.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "feb990f975945502ac47d0a2f62276b57865061753c9fed4d4cec82a8a289b15", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bc01a71bc76f1c9af29107550ebe5cde09e32ecc64e502f2ac3cc64c2439aacf", "generation_seconds_batch": 20.39060562895611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0454659461975098, "target_z": 0.660156159068296, "ce": 6.459460258483887, "genuineness": 4.118232727050781, "identity": 0.4001084566116333, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/feb990f975945502ac47d0a2f62276b57865061753c9fed4d4cec82a8a289b15.mp3" }, { "id": "emo_Interest-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-1", "key": "fec98dcf9da748d9b9cf7ed066617438d15f898c2b1552fedecc93ad43937408", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0d0f1c248b19566bfc1dfbcbc2f610ae706e169946272833da52305c0dc4ed3b", "generation_seconds_batch": 22.204011281952262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.238283634185791, "target_z": 0.8710936840299403, "ce": 6.427689552307129, "genuineness": 4.13078498840332, "identity": 0.6001741886138916, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fec98dcf9da748d9b9cf7ed066617438d15f898c2b1552fedecc93ad43937408.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "fee40a673f743e6ea5327bc2ea7d61def4eab33c7afbab9596cc15f5a890b4a0", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8badba506b5e401ac7ac7225d3523ac7f179506bfaa25b8ba18f2763b3dbe28f", "generation_seconds_batch": 15.042887161951512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3204097747802734, "target_z": 0.9609375412631262, "ce": 6.260893821716309, "genuineness": 4.519899368286133, "identity": 0.7328378558158875, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/fee40a673f743e6ea5327bc2ea7d61def4eab33c7afbab9596cc15f5a890b4a0.mp3" }, { "id": "emo_Interest-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-de-0", "key": "ff64e902a632080ce5d0aefb1e3d7c608d8149d36563958a7b8d476eb536089e", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Die Tür ist noch offen.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "070d33aee13cca2799647eee9a68bb6c2397352c5624c6d7c2a247d1663efdf3", "generation_seconds_batch": 16.83194933796767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2775614261627197, "target_z": 0.9140625646965065, "ce": 6.340320587158203, "genuineness": 4.545003414154053, "identity": 0.42965608835220337, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ff64e902a632080ce5d0aefb1e3d7c608d8149d36563958a7b8d476eb536089e.mp3" }, { "id": "emo_Interest-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-fr-1", "key": "ff6e1c70920f3e093ee14c1e594ee8aee9faffca683d9a6f294e4758032ecf87", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "00a62ce25d3dea61d732b18252dccd0b151838955906b2e391d30a0e9b95fa86", "generation_seconds_batch": 21.2093383789761, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.88457989692688, "target_z": 1.5781249500767116, "ce": 5.903473377227783, "genuineness": 4.319066047668457, "identity": 0.5315889716148376, "hypothesis": "J'ai trouvé la petite boîte ! Elle était près. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ff6e1c70920f3e093ee14c1e594ee8aee9faffca683d9a6f294e4758032ecf87.mp3" }, { "id": "emo_Interest-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Interest-nl-1", "key": "ffb7015a399a8258307d916b9da917efbee270a631232b4703e57883f14ba96c", "bucket": "emo_Interest", "phase": "grid", "candidate": "manual-bb77d46f4025", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Convey an active, vibrant eagerness; the emotion should feel like the thrill of an unexpected and delightful revelation.\nSCRIPT:\n(Start with a quick, energized breath supporting an immediate surge of vocal enthusiasm.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Use rapid, subtle shifts in vocal color and texture to reflect the speed of mental processing.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final word with an emphatic, open resonance, fully releasing the sense of wonder.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3db7bb66b237b29d0558c42b569dc91aa610ae7f793593ea127e007e60b9b8c9", "generation_seconds_batch": 22.554005510988645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.591782569885254, "target_z": 1.2578123059104804, "ce": 6.268836498260498, "genuineness": 4.293961524963379, "identity": 0.6824847459793091, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Interest/ffb7015a399a8258307d916b9da917efbee270a631232b4703e57883f14ba96c.mp3" }, { "key": "original-emo_Interest-de-0-seed1701-scale0.0", "bucket": "emo_Interest", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "752859bf3f994e87bc8b74a76bddaa174ff7bd94ca45d436c6a7f490187d6cb6", "task_id": "emo_Interest-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. 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": 1.6312651634216309, "target_z": 0.2070312986497352, "ce": 6.324435234069824, "genuineness": 4.519899368286133, "identity": 0.540902316570282, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/d75318a0b1312dd4549ac7f7.mp3" }, { "key": "original-emo_Interest-de-0-seed1701-scale0.5", "bucket": "emo_Interest", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "eada4e997fb4e9920d5cb5f9cf64d7ddeab7962f4306a7ec802acba863693211", "task_id": "emo_Interest-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. 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": 1.9097795486450195, "target_z": 0.5117187767446189, "ce": 6.292664527893066, "genuineness": 4.582659721374512, "identity": 0.4376763105392456, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/046f7e69558778408fb55f98.mp3" }, { "key": "original-emo_Interest-de-0-seed1701-scale0.75", "bucket": "emo_Interest", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "d6d9fbec47b3b79154b55ff871ba5bdfd3c32ebeb5effe4b9660f193bfa32578", "task_id": "emo_Interest-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. 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": 1.7776637077331543, "target_z": 0.36718749032099507, "ce": 6.308549880981445, "genuineness": 4.545003414154053, "identity": 0.5808408260345459, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/63e10ae1881845343dc59828.mp3" }, { "key": "original-emo_Interest-de-0-seed1701-scale1.0", "bucket": "emo_Interest", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "4040f4940af50af804fd21ca8849d124fd5395b24006dc90adb15a6513aa1b8d", "task_id": "emo_Interest-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. 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": 1.8419362306594849, "target_z": 0.4374999551709246, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.39502260088920593, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/17aff38e8e58b6f6b54241a2.mp3" }, { "key": "original-emo_Interest-de-0-seed1702-scale0.0", "bucket": "emo_Interest", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "3a6489ad7b145330eebbe53e095cc040956318d5f73d305f8fda8d89e38271bc", "task_id": "emo_Interest-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. 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": 1.7223179340362549, "target_z": 0.30664065645676597, "ce": 6.229123115539551, "genuineness": 4.444586753845215, "identity": 0.508020281791687, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/f7d2b05589ce99527f654363.mp3" }, { "key": "original-emo_Interest-de-0-seed1702-scale0.5", "bucket": "emo_Interest", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "89524023f4fe8be005395d0fe3dc41952e82da29345d99214e3d333dbf1efbf3", "task_id": "emo_Interest-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. 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": 1.820512056350708, "target_z": 0.4140624668876148, "ce": 6.260893821716309, "genuineness": 4.557555198669434, "identity": 0.6855511665344238, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/be4906ebbb3f3ee302ffdeb6.mp3" }, { "key": "original-emo_Interest-de-0-seed1702-scale0.75", "bucket": "emo_Interest", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "7e145169b6ba10bd4e8c2756a6775fceb9ca8c3ac6da8df9c6e8365983a6ed76", "task_id": "emo_Interest-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. 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": 1.8633604049682617, "target_z": 0.4609374434542345, "ce": 6.197352409362793, "genuineness": 4.369274139404297, "identity": 0.4984668493270874, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/2d49c3f1a3a8f367a9ce1384.mp3" }, { "key": "original-emo_Interest-de-0-seed1702-scale1.0", "bucket": "emo_Interest", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "104468dcd1f3ea4c312c75023a9d2b88ff6bca96ef21ce1ec7e1de7ffdc2463c", "task_id": "emo_Interest-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Interest. 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": 1.8758578300476074, "target_z": 0.47460930075184393, "ce": 6.23706579208374, "genuineness": 4.457139015197754, "identity": 0.6625282168388367, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/d86b2a136bc1a00b32507295.mp3" }, { "key": "original-emo_Interest-de-1-seed1701-scale0.0", "bucket": "emo_Interest", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "dea5066165311a86a047291a5a1d407cf2fd9cbfcefee28d5a9d73b70ee6e040", "task_id": "emo_Interest-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. 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": 2.106167793273926, "target_z": 0.7265623976063165, "ce": 6.284721851348877, "genuineness": 4.262581825256348, "identity": 0.45719048380851746, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/626d54dfd2e37b38d3768ee9.mp3" }, { "key": "original-emo_Interest-de-1-seed1701-scale0.5", "bucket": "emo_Interest", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "4043b00f24f0568855e24cb279e528ac162437fe231cc3034e983f4d08ad4e93", "task_id": "emo_Interest-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. 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": 2.052607536315918, "target_z": 0.6679688725158253, "ce": 6.38003396987915, "genuineness": 4.381826400756836, "identity": 0.5043102502822876, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/048682fd2744e1c3f12df5ac.mp3" }, { "key": "original-emo_Interest-de-1-seed1701-scale0.75", "bucket": "emo_Interest", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "e1e788c3243a057bc9ae17acb09be6f27012a9e0e02b1b829e4f6f654d6f5dc1", "task_id": "emo_Interest-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. 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": 2.3311219215393066, "target_z": 0.972656350610709, "ce": 6.403861999511719, "genuineness": 4.432034492492676, "identity": 0.5832929611206055, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/e82a8dfee6d62093e717e3fc.mp3" }, { "key": "original-emo_Interest-de-1-seed1701-scale1.0", "bucket": "emo_Interest", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "c4e34b2972acd6b4930aa2652207ee6fa1971b4329c4a08416ab55f40ed81128", "task_id": "emo_Interest-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. 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": 2.34183406829834, "target_z": 0.9843751599582917, "ce": 6.403861999511719, "genuineness": 4.413206577301025, "identity": 0.36597952246665955, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/35c0a7db3331be4fef064d1f.mp3" }, { "key": "original-emo_Interest-de-1-seed1702-scale0.0", "bucket": "emo_Interest", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "8df2e92f3b3f7f5d0d19169142b3f5211c1875e78cd7975e9c271058568661f1", "task_id": "emo_Interest-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. 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": 2.0276126861572266, "target_z": 0.6406251579206065, "ce": 6.443574905395508, "genuineness": 4.425758361816406, "identity": 0.4939824640750885, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/50c9b2c37afae8250439472e.mp3" }, { "key": "original-emo_Interest-de-1-seed1702-scale0.5", "bucket": "emo_Interest", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "133add53df2ee730673dd0e4504dca99d28f14775149a8e507baf23d4a693b82", "task_id": "emo_Interest-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. 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": 1.881213903427124, "target_z": 0.4804687054256353, "ce": 6.395919322967529, "genuineness": 4.337893962860107, "identity": 0.5762849450111389, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/16f6db499cca070986a22f98.mp3" }, { "key": "original-emo_Interest-de-1-seed1702-scale0.75", "bucket": "emo_Interest", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "f6c3090732cd478eee6fe1308654165774ead887092d18488191e0539fceff12", "task_id": "emo_Interest-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. 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": 2.166869640350342, "target_z": 0.792968636144337, "ce": 6.372091293334961, "genuineness": 4.149612903594971, "identity": 0.45977914333343506, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/3b901184ec627a88aa23b3ad.mp3" }, { "key": "original-emo_Interest-de-1-seed1702-scale1.0", "bucket": "emo_Interest", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "9406027bdb8fa2610180e8d6c14b97065b1caf1eb080df3972d5af7dfafd5e72", "task_id": "emo_Interest-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Interest. 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": 1.9204915761947632, "target_z": 0.5234374556803459, "ce": 6.395919322967529, "genuineness": 4.068024158477783, "identity": 0.4901280403137207, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/de/9bc8272dea140ca6cb838058.mp3" }, { "key": "original-emo_Interest-en-0-seed1701-scale0.0", "bucket": "emo_Interest", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "69d703fd0988f1c53a6e8bff17174fb108c8f6e5dcb86f82f40ac152d9d5d8e3", "task_id": "emo_Interest-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. 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": 1.97405207157135, "target_z": 0.5820312415945483, "ce": 6.133810997009277, "genuineness": 4.13078498840332, "identity": 0.3585788607597351, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/69dc93fbde8b1b01e75af034.mp3" }, { "key": "original-emo_Interest-en-0-seed1701-scale0.5", "bucket": "emo_Interest", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "9e37db6d780d13d81ab1db08dadfa6aca5371a808065c8d29b58e60fb4719cfa", "task_id": "emo_Interest-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. 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": 2.10973858833313, "target_z": 0.7304687543300812, "ce": 6.324435234069824, "genuineness": 4.356721878051758, "identity": 0.15165194869041443, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/d504f693393773f819d41ff8.mp3" }, { "key": "original-emo_Interest-en-0-seed1701-scale0.75", "bucket": "emo_Interest", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "302aede348bb2d24bc2a86bb42ede0247cbfa58976d33cc8af7439d2e9f658cf", "task_id": "emo_Interest-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. 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": 2.1490163803100586, "target_z": 0.7734376349966474, "ce": 6.268836498260498, "genuineness": 4.281409740447998, "identity": 0.37174463272094727, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/93c71e1cd1ea8f271c26e473.mp3" }, { "key": "original-emo_Interest-en-0-seed1701-scale1.0", "bucket": "emo_Interest", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "9ae3631539adc22cb4c1e6d94cd10ea78419ddbad6392b9c50f115c161dade6d", "task_id": "emo_Interest-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. 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": 2.0169005393981934, "target_z": 0.6289063485730237, "ce": 6.38797664642334, "genuineness": 3.948779582977295, "identity": 0.36089926958084106, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/9602103afb7698e30e7b7f00.mp3" }, { "key": "original-emo_Interest-en-0-seed1702-scale0.0", "bucket": "emo_Interest", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "965a2bd4b1a2a5a981840a8c73bf7add1a04ddafa991fc365e43f623f0759072", "task_id": "emo_Interest-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. 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": 2.2668492794036865, "target_z": 0.9023437553489237, "ce": 6.149696350097656, "genuineness": 3.936227321624756, "identity": 0.29285985231399536, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/7c1c3c6953c9518b1072c204.mp3" }, { "key": "original-emo_Interest-en-0-seed1702-scale0.5", "bucket": "emo_Interest", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "68edc9680acb98062c449afa2cba8c49059f39259f69e135c4731de233d28bb7", "task_id": "emo_Interest-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. 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": 1.9383450746536255, "target_z": 0.5429687176517467, "ce": 6.2767791748046875, "genuineness": 3.9550557136535645, "identity": 0.28001296520233154, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/85aa080f9fed43d1b9b49d25.mp3" }, { "key": "original-emo_Interest-en-0-seed1702-scale0.75", "bucket": "emo_Interest", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "2b8e19a0c06d3ac621114ac7558e555a0bfd1847192b51da50badf33b9f3bdbc", "task_id": "emo_Interest-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. 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": 1.94191575050354, "target_z": 0.5468749439636558, "ce": 6.070269584655762, "genuineness": 3.7918784618377686, "identity": 0.32342079281806946, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/de8d26052e4a3d31bcf22831.mp3" }, { "key": "original-emo_Interest-en-0-seed1702-scale1.0", "bucket": "emo_Interest", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "0aa050e6c333616723ef394e65556616796ff2a5bf4dab10b2511dd8ccfd965b", "task_id": "emo_Interest-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Interest. 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": 1.8455069065093994, "target_z": 0.44140618148283367, "ce": 6.2767791748046875, "genuineness": 4.105680465698242, "identity": 0.22783203423023224, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/5fed7bc15ef7fcd641392c0e.mp3" }, { "key": "original-emo_Interest-en-1-seed1701-scale0.0", "bucket": "emo_Interest", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "78b863d1e0619692493420dd2f1677cb06b65f38da66c8599ba1e17fcfbf7379", "task_id": "emo_Interest-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. 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": 2.591782569885254, "target_z": 1.2578123059104804, "ce": 6.292664527893066, "genuineness": 4.105680465698242, "identity": 0.43545258045196533, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/8974e9901befeb6bc1952e11.mp3" }, { "key": "original-emo_Interest-en-1-seed1701-scale0.5", "bucket": "emo_Interest", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "462d13666dd3fcbb9c773397123cf2e908117881ba4edf22162db74ec39b15e5", "task_id": "emo_Interest-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. 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": 2.4275307655334473, "target_z": 1.078125113091531, "ce": 6.308549880981445, "genuineness": 4.570107460021973, "identity": 0.4758850932121277, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/b758c02d3d7fd6cfb8a588af.mp3" }, { "key": "original-emo_Interest-en-1-seed1701-scale0.75", "bucket": "emo_Interest", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "fe358599084aa02f52ee85a2fb0cf44e82749aaa113af63f9fdb0ac0b530eddf", "task_id": "emo_Interest-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. 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": 2.5489344596862793, "target_z": 1.210937590167572, "ce": 6.403861999511719, "genuineness": 4.494794845581055, "identity": 0.45103275775909424, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/e4dc7cc4fcb57c464de68e41.mp3" }, { "key": "original-emo_Interest-en-1-seed1701-scale1.0", "bucket": "emo_Interest", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "822f792039c4b3410e9bb38981a525774ae41cd89bebbeba9999d97ef989d2ae", "task_id": "emo_Interest-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. 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": 2.713186502456665, "target_z": 1.3906250438102328, "ce": 6.4912309646606445, "genuineness": 4.457139015197754, "identity": 0.32867687940597534, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/782cfd4cce9bd4ca013fc6e3.mp3" }, { "key": "original-emo_Interest-en-1-seed1702-scale0.0", "bucket": "emo_Interest", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "b407c30f76b3e5478d680fde445ceeb3b8de6a08caaac13c1c8384718bbde900", "task_id": "emo_Interest-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. 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": 2.6774795055389404, "target_z": 1.351562519867431, "ce": 6.348263263702393, "genuineness": 4.3881025314331055, "identity": 0.3854193389415741, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/6be947f92e42df461ab78972.mp3" }, { "key": "original-emo_Interest-en-1-seed1702-scale0.5", "bucket": "emo_Interest", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "7859177f3ef5f1bdcc54285a307d59da2d7805d37d1cb2bf8052334931876892", "task_id": "emo_Interest-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. 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": 2.584641456604004, "target_z": 1.2500001141103736, "ce": 6.268836498260498, "genuineness": 4.143336772918701, "identity": 0.274050235748291, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/668be4c3e5e96e1588e75f33.mp3" }, { "key": "original-emo_Interest-en-1-seed1702-scale0.75", "bucket": "emo_Interest", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "c7201db8f71d025419e7512651847643c898cc27df2ce133bd8bfe492bc88c2c", "task_id": "emo_Interest-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. 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": 2.898862838745117, "target_z": 1.593750116148059, "ce": 6.2767791748046875, "genuineness": 4.419482707977295, "identity": 0.33854246139526367, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/2f7618eb942214cc55f323e2.mp3" }, { "key": "original-emo_Interest-en-1-seed1702-scale1.0", "bucket": "emo_Interest", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "b948f27907f6add9679ea950bc149798434ccfe8e97f4bd6087b2733f4f3dd0d", "task_id": "emo_Interest-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Interest. 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": 2.656055450439453, "target_z": 1.3281251619959769, "ce": 6.395919322967529, "genuineness": 4.444586753845215, "identity": 0.36481207609176636, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/en/8a352caf35ed449bfb36e41f.mp3" }, { "key": "original-emo_Interest-es-0-seed1701-scale0.0", "bucket": "emo_Interest", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "7f05912d229d2c40636112a03091155f794657e6dde82e7054b59be947ef299e", "task_id": "emo_Interest-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. 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": 1.9097795486450195, "target_z": 0.5117187767446189, "ce": 6.221180438995361, "genuineness": 4.118232727050781, "identity": 0.5400984883308411, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/15eb1350ccdc68aef5c15865.mp3" }, { "key": "original-emo_Interest-es-0-seed1701-scale0.5", "bucket": "emo_Interest", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "5904914f30cb8b81782bfd0afbde381585084b90c4110742f76605f3d9103720", "task_id": "emo_Interest-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. 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": 1.8562190532684326, "target_z": 0.4531249908304164, "ce": 6.054384231567383, "genuineness": 4.011539936065674, "identity": 0.44013890624046326, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/56ad75ee77f7398342b6f06d.mp3" }, { "key": "original-emo_Interest-es-0-seed1701-scale0.75", "bucket": "emo_Interest", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "b64e2ebd2a5b2ba34fc9782d130e9d18bd264ddc2b67e92de57676acb2ec50fe", "task_id": "emo_Interest-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. 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": 2.170440435409546, "target_z": 0.7968749928681016, "ce": 6.141753673553467, "genuineness": 4.256305694580078, "identity": 0.7738528251647949, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/87483f5684e26b20336b2814.mp3" }, { "key": "original-emo_Interest-es-0-seed1701-scale1.0", "bucket": "emo_Interest", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "0b9606ade602c7c37a104c6b0a226275aa30d06f671056aa3967e0feb28a2c32", "task_id": "emo_Interest-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. 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": 1.8365802764892578, "target_z": 0.4316406809089889, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.5190770626068115, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/f51953c3625409a9e4d4daad.mp3" }, { "key": "original-emo_Interest-es-0-seed1702-scale0.0", "bucket": "emo_Interest", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "640015c367fc1e71b5e632ab1f5aa12a1aba57a2efbe36f5cbdaf106b6ced1fe", "task_id": "emo_Interest-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. 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": 2.4418134689331055, "target_z": 1.0937500183391673, "ce": 6.109982967376709, "genuineness": 4.1998209953308105, "identity": 0.3133538067340851, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/45597c591a7b86e2e6b15f72.mp3" }, { "key": "original-emo_Interest-es-0-seed1702-scale0.5", "bucket": "emo_Interest", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "eba36bdc280d20ff5be6876c8f529585f6805a3e9e9ae206f3042edb5b5f9b57", "task_id": "emo_Interest-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. 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": 2.170440435409546, "target_z": 0.7968749928681016, "ce": 5.974957466125488, "genuineness": 3.8671910762786865, "identity": 0.429177463054657, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/8f3b131ab9fb0237b98006dd.mp3" }, { "key": "original-emo_Interest-es-0-seed1702-scale0.75", "bucket": "emo_Interest", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "36bc1a4fe897d342e123db141aeaf7c1b74568a43730b15f1803ffe240b3a438", "task_id": "emo_Interest-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. 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": 2.070460796356201, "target_z": 0.6874998736635148, "ce": 6.070269584655762, "genuineness": 4.124508857727051, "identity": 0.4580788016319275, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/b86a23d1365094a30c5ceeeb.mp3" }, { "key": "original-emo_Interest-es-0-seed1702-scale1.0", "bucket": "emo_Interest", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "3c01d326819bd73bee5ede530d2408213603c34d91e420c0824f7031f4e11114", "task_id": "emo_Interest-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Interest. 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": 2.0918850898742676, "target_z": 0.7109374923586803, "ce": 6.141753673553467, "genuineness": 4.300237655639648, "identity": 0.27831658720970154, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/91d3140f64fb43627ff0f03a.mp3" }, { "key": "original-emo_Interest-es-1-seed1701-scale0.0", "bucket": "emo_Interest", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "123be4f5a6bb0690aa27b7ec4f3535f7d7d648f2426d098a8ffc0f9569b9087b", "task_id": "emo_Interest-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. 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": 2.6774795055389404, "target_z": 1.351562519867431, "ce": 6.24500846862793, "genuineness": 4.582659721374512, "identity": 0.7609536647796631, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/c9d33951e90f3a95e23c96f5.mp3" }, { "key": "original-emo_Interest-es-1-seed1701-scale0.5", "bucket": "emo_Interest", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "94c8e3b6f8d7cf856d5996f9afb803420366a216277d7b3271c766bbbdf4d463", "task_id": "emo_Interest-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. 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": 2.5703585147857666, "target_z": 1.2343749480390263, "ce": 6.086154937744141, "genuineness": 4.425758361816406, "identity": 0.5752211213111877, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/a06b7badf2463c280bca8392.mp3" }, { "key": "original-emo_Interest-es-1-seed1701-scale0.75", "bucket": "emo_Interest", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "078de547a77c0691ade19b56ec26c2bcfd5a76b1a73c3447818a9980104b09ad", "task_id": "emo_Interest-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. 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": 2.663196563720703, "target_z": 1.3359373537960837, "ce": 6.070269584655762, "genuineness": 4.65797233581543, "identity": 0.6849982142448425, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/b39106a886178dcfba6d8c55.mp3" }, { "key": "original-emo_Interest-es-1-seed1701-scale1.0", "bucket": "emo_Interest", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "ee4e4387cfd421db7c1e43514c6d6f4f09a28ae06395d3e3fc0ecab839a01510", "task_id": "emo_Interest-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. 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": 2.541792869567871, "target_z": 1.2031248767200426, "ce": 6.221180438995361, "genuineness": 4.394378662109375, "identity": 0.6400991678237915, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/aee3e0dbe89d6ae25373c0d1.mp3" }, { "key": "original-emo_Interest-es-1-seed1702-scale0.0", "bucket": "emo_Interest", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "5d768b1410516734341de9289ae0d6f209653fd526d35290f9f207f768a72baf", "task_id": "emo_Interest-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. 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": 2.598924160003662, "target_z": 1.2656250193580099, "ce": 6.229123115539551, "genuineness": 4.557555198669434, "identity": 0.5315434336662292, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/45c2ed5b5d692348d67bb438.mp3" }, { "key": "original-emo_Interest-es-1-seed1702-scale0.5", "bucket": "emo_Interest", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "91f73f80d6f372c1b0749224ef7afa5ec1d93cdab1dc2aad9c80469aba761015", "task_id": "emo_Interest-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. 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": 2.4560961723327637, "target_z": 1.1093749235868033, "ce": 6.070269584655762, "genuineness": 4.344170093536377, "identity": 0.6501307487487793, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/2ede7b42ed3cc287a74378f4.mp3" }, { "key": "original-emo_Interest-es-1-seed1702-scale0.75", "bucket": "emo_Interest", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "aa465835e59ef59cc380762f1b356a9c1f10a8f7230d964170c97b5fddf637b3", "task_id": "emo_Interest-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. 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": 2.4918031692504883, "target_z": 1.1484374475296049, "ce": 6.0146708488464355, "genuineness": 4.3504462242126465, "identity": 0.5898069143295288, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/4f3916a5400193575e2b521f.mp3" }, { "key": "original-emo_Interest-es-1-seed1702-scale1.0", "bucket": "emo_Interest", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "6a733d337d04a5a13767ff250214cc346a122516afc2d8effd635b941a505b56", "task_id": "emo_Interest-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Interest. 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": 2.6132068634033203, "target_z": 1.281249924605646, "ce": 6.1020402908325195, "genuineness": 4.7332844734191895, "identity": 0.521647036075592, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/es/d9260a1ca56678218ac94b4c.mp3" }, { "key": "original-emo_Interest-fr-0-seed1701-scale0.0", "bucket": "emo_Interest", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "c81bd4988f9657d13ffd4540a8d38b7efc42d18c512f751cdc08f82a514de9c2", "task_id": "emo_Interest-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. 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": 1.6973230838775635, "target_z": 0.2792969418615471, "ce": 6.149696350097656, "genuineness": 4.369274139404297, "identity": 0.7238190770149231, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/8374f1bf0774f9621dee4315.mp3" }, { "key": "original-emo_Interest-fr-0-seed1701-scale0.5", "bucket": "emo_Interest", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "6c1449242e524d8de85ca5488080bd7d6cd1436b842a0da0b929be5eb482dc52", "task_id": "emo_Interest-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. 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": 1.660723328590393, "target_z": 0.23925776353187647, "ce": 6.24500846862793, "genuineness": 4.444586753845215, "identity": 0.7343682646751404, "hypothesis": "La porte 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/emo_Interest/fr/73050173e2eb8d97db76aa4a.mp3" }, { "key": "original-emo_Interest-fr-0-seed1701-scale0.75", "bucket": "emo_Interest", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "afd3164b00b6ffa7b3c0f367730b6a2fc0e7172b325a0930921fc1079f2f353f", "task_id": "emo_Interest-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. 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": 1.8794286251068115, "target_z": 0.4785156574756086, "ce": 6.09409761428833, "genuineness": 4.2751336097717285, "identity": 0.7040596008300781, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/8ad94f656a097acfb6814bbc.mp3" }, { "key": "original-emo_Interest-fr-0-seed1701-scale1.0", "bucket": "emo_Interest", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "158ab34da02e8a365d24a72272d158a1be2c67f522e5462aa28ee98812a8c35f", "task_id": "emo_Interest-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. 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": 1.8562190532684326, "target_z": 0.4531249908304164, "ce": 6.173524379730225, "genuineness": 4.6705241203308105, "identity": 0.6810380220413208, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/f06b81dbea5a5a45e8dc8042.mp3" }, { "key": "original-emo_Interest-fr-0-seed1702-scale0.0", "bucket": "emo_Interest", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "167b7a06d5779ee3a6d5c0392f0cc7771b85534e6cf7a7d228ca8e9f115df9ae", "task_id": "emo_Interest-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. 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": 1.8098000288009644, "target_z": 0.4023437879518877, "ce": 6.1020402908325195, "genuineness": 4.507347106933594, "identity": 0.6290590167045593, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/4712c5a16190c7d8ad92cafd.mp3" }, { "key": "original-emo_Interest-fr-0-seed1702-scale0.5", "bucket": "emo_Interest", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "8aabbde4eea0cb74ecaadc34158d19e2d42e6d02f12ef764c52ca12a84943566", "task_id": "emo_Interest-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. 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": 2.0204710960388184, "target_z": 0.632812444473077, "ce": 6.181467056274414, "genuineness": 4.243753433227539, "identity": 0.583986759185791, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/613c9a9acae33192c72acb1b.mp3" }, { "key": "original-emo_Interest-fr-0-seed1702-scale0.75", "bucket": "emo_Interest", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "d4b36df36963f116e2c8873a2c3095a5e5789acf61747d839d5f6517ca1217ae", "task_id": "emo_Interest-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. 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": 2.056178092956543, "target_z": 0.6718749684158787, "ce": 6.173524379730225, "genuineness": 4.20609712600708, "identity": 0.6345962285995483, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/d624402b5109e064c8ed079c.mp3" }, { "key": "original-emo_Interest-fr-0-seed1702-scale1.0", "bucket": "emo_Interest", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "a7171b1c69f9893fb7a27258292874f9732b97acfdbe3a940ee39880d5efd50f", "task_id": "emo_Interest-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Interest. 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": 1.999047040939331, "target_z": 0.6093750866016229, "ce": 6.0305562019348145, "genuineness": 3.948779582977295, "identity": 0.6691590547561646, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/2e42b6e95cccde3488d45bc7.mp3" }, { "key": "original-emo_Interest-fr-1-seed1701-scale0.0", "bucket": "emo_Interest", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "5fcaf25d59525d45a7f6f8922eb07426ea17e7ee4b5708acc8de0f2af0df1a44", "task_id": "emo_Interest-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. 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": 2.120450735092163, "target_z": 0.7421875636776639, "ce": 6.157639026641846, "genuineness": 4.469690799713135, "identity": 0.5044088363647461, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/e1adce49212934b26d641098.mp3" }, { "key": "original-emo_Interest-fr-1-seed1701-scale0.5", "bucket": "emo_Interest", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "5322daf8bf64747a4dc313d8ba6e6193202e7190932c10654f368224de5e90b8", "task_id": "emo_Interest-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. 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": 2.1954352855682373, "target_z": 0.8242187074633205, "ce": 6.229123115539551, "genuineness": 4.532451152801514, "identity": 0.7741289138793945, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/9eb0bc037f37541d4ea7ccd5.mp3" }, { "key": "original-emo_Interest-fr-1-seed1701-scale0.75", "bucket": "emo_Interest", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "cfab61e61b0f6630973f6d8bbcf633293661382f1cf60789187b4d26d41198f6", "task_id": "emo_Interest-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. 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": 2.2775614261627197, "target_z": 0.9140625646965065, "ce": 6.165581703186035, "genuineness": 4.507347106933594, "identity": 0.6702128052711487, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/506675cfa6d9ae1fdbaa3660.mp3" }, { "key": "original-emo_Interest-fr-1-seed1701-scale1.0", "bucket": "emo_Interest", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "068a6350fd8c69562f5ad6eeff39aecb5574622d902fb3f544dfbbd5bb0f3287", "task_id": "emo_Interest-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. 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": 1.7740930318832397, "target_z": 0.36328126400908606, "ce": 6.109982967376709, "genuineness": 4.482243061065674, "identity": 0.7876945734024048, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/5220a0aac4f2c3dc2cb7eb11.mp3" }, { "key": "original-emo_Interest-fr-1-seed1702-scale0.0", "bucket": "emo_Interest", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "d45dd5212a65c41da7505ed06718d5951cf4fdc6e9548fbe1d473440bfca21d3", "task_id": "emo_Interest-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. 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": 2.177581787109375, "target_z": 0.8046874454919197, "ce": 6.23706579208374, "genuineness": 4.532451152801514, "identity": 0.6990880966186523, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/45897f101f7d201f2427a6d1.mp3" }, { "key": "original-emo_Interest-fr-1-seed1702-scale0.5", "bucket": "emo_Interest", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "5a416ebea22b3114b160e4c5fd01997726e7cd51f931687e617234b535f0e958", "task_id": "emo_Interest-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. 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": 2.106167793273926, "target_z": 0.7265623976063165, "ce": 6.133810997009277, "genuineness": 4.494794845581055, "identity": 0.7004334926605225, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/116ba9386750378e8e2d9072.mp3" }, { "key": "original-emo_Interest-fr-1-seed1702-scale0.75", "bucket": "emo_Interest", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "a160ebce1438f9b70dbc3a9475746b904419b53a477dd3b07857e0d4213413a7", "task_id": "emo_Interest-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. 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": 2.052607536315918, "target_z": 0.6679688725158253, "ce": 6.23706579208374, "genuineness": 4.532451152801514, "identity": 0.7814971208572388, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/d2799673739febd96cceed5f.mp3" }, { "key": "original-emo_Interest-fr-1-seed1702-scale1.0", "bucket": "emo_Interest", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "3727db0e1118d4cd2eee33c061924d673b7c8bf4acb51f69435bb94df45d6020", "task_id": "emo_Interest-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Interest. 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": 2.0454659461975098, "target_z": 0.660156159068296, "ce": 6.229123115539551, "genuineness": 4.6203155517578125, "identity": 0.8186060786247253, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/fr/473c6bbc1c70eb1004cc43ec.mp3" }, { "key": "original-emo_Interest-nl-0-seed1701-scale0.0", "bucket": "emo_Interest", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "a0e3f59b8750f094c90fa9762e6e8500768e2ef46c10643d1555db08b44d7fef", "task_id": "emo_Interest-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. 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": 2.0169005393981934, "target_z": 0.6289063485730237, "ce": 6.09409761428833, "genuineness": 4.218649387359619, "identity": 0.7083092927932739, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/c1f35b8d502a4bf04eedf9e2.mp3" }, { "key": "original-emo_Interest-nl-0-seed1701-scale0.5", "bucket": "emo_Interest", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "aa84245f8a0f4947843aed6161e8c15acc89eb6e6d23640adef0fe76a06d9b5c", "task_id": "emo_Interest-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. 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": 1.999047040939331, "target_z": 0.6093750866016229, "ce": 6.1894097328186035, "genuineness": 4.243753433227539, "identity": 0.6099141836166382, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Oh.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/8302df11b2a85282d096762a.mp3" }, { "key": "original-emo_Interest-nl-0-seed1701-scale0.75", "bucket": "emo_Interest", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "39101b7b98282af3c3769076148d20bd5396fe0befcdf17911283d1e5e715df0", "task_id": "emo_Interest-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. 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": 2.2597079277038574, "target_z": 0.8945313027251057, "ce": 6.173524379730225, "genuineness": 4.080576419830322, "identity": 0.7658120393753052, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/7500578e838b268d66ca27c7.mp3" }, { "key": "original-emo_Interest-nl-0-seed1701-scale1.0", "bucket": "emo_Interest", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "fd4c0ba9d69a74ce2b7e0379229f2be04954d411435e79f968d24de36209af6f", "task_id": "emo_Interest-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. 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": 2.0883145332336426, "target_z": 0.7070313964586269, "ce": 6.157639026641846, "genuineness": 4.300237655639648, "identity": 0.5627490878105164, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/0bb629b265c41ced0b97c966.mp3" }, { "key": "original-emo_Interest-nl-0-seed1702-scale0.0", "bucket": "emo_Interest", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "bb5f80a1aef20f84e3e5f70cdab1f5fdacc7f95566b929b185d66b0bcff4a7b1", "task_id": "emo_Interest-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. 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": 1.8026585578918457, "target_z": 0.39453120491621396, "ce": 5.935244083404541, "genuineness": 4.356721878051758, "identity": 0.627290666103363, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/eac88ecf69cf5ccce20f8349.mp3" }, { "key": "original-emo_Interest-nl-0-seed1702-scale0.5", "bucket": "emo_Interest", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "cf90ba043aa05ff88469ee91c12180c93ac67a744953507bf20b368241557730", "task_id": "emo_Interest-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. 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": 2.063319444656372, "target_z": 0.6796874210396968, "ce": 6.09409761428833, "genuineness": 4.105680465698242, "identity": 0.7132329940795898, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/df0aa251005bcf7af53943df.mp3" }, { "key": "original-emo_Interest-nl-0-seed1702-scale0.75", "bucket": "emo_Interest", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "0686bdb8507ac1ad3b491263e771dca0beb6f729816140042239ea439ff529a4", "task_id": "emo_Interest-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. 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": 1.9240622520446777, "target_z": 0.527343681992255, "ce": 6.054384231567383, "genuineness": 4.017816066741943, "identity": 0.6482448577880859, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/2fe3c8969c724bac7b7e20df.mp3" }, { "key": "original-emo_Interest-nl-0-seed1702-scale1.0", "bucket": "emo_Interest", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "857ec5e3db7d2e863830a2a21dc0158380aee3805a854d8d762faf7c98c84677", "task_id": "emo_Interest-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Interest. 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": 1.9490572214126587, "target_z": 0.5546875269993294, "ce": 6.054384231567383, "genuineness": 4.118232727050781, "identity": 0.612999439239502, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/c92ff9b89c148a878925d7dc.mp3" }, { "key": "original-emo_Interest-nl-1-seed1701-scale0.0", "bucket": "emo_Interest", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "7a326d0940276e711902db08b8b06653d9da4c7ba6c8f49b17763bd48b9057e8", "task_id": "emo_Interest-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. 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": 2.1490163803100586, "target_z": 0.7734376349966474, "ce": 6.165581703186035, "genuineness": 4.425758361816406, "identity": 0.7177962064743042, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/02f9f0b2d02fca07f4d4ad11.mp3" }, { "key": "original-emo_Interest-nl-1-seed1701-scale0.5", "bucket": "emo_Interest", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "c55c0c78a478a9dd2c085155497ee88abc3486bcdfb830773c6f8b4057a539b5", "task_id": "emo_Interest-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. 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": 2.1454455852508545, "target_z": 0.7695312782728828, "ce": 6.133810997009277, "genuineness": 4.218649387359619, "identity": 0.7398459911346436, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/5e47cbde5975cd89305ef85a.mp3" }, { "key": "original-emo_Interest-nl-1-seed1701-scale0.75", "bucket": "emo_Interest", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "f046fcc56dde8d663082f954ac5a81bf4d4cb0ed603f752973827716761e4145", "task_id": "emo_Interest-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. 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": 2.2061474323272705, "target_z": 0.8359375168109032, "ce": 6.157639026641846, "genuineness": 4.356721878051758, "identity": 0.6936620473861694, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/666512bad1e5b5913b853f76.mp3" }, { "key": "original-emo_Interest-nl-1-seed1701-scale1.0", "bucket": "emo_Interest", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "7ef8df0903bec8d086f5d91dd4ea62bff0f1d75e39e688603cffa803e8b2e7a1", "task_id": "emo_Interest-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. 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": 2.352545976638794, "target_z": 0.9960937084821632, "ce": 6.173524379730225, "genuineness": 4.432034492492676, "identity": 0.7506815195083618, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/28e200dce29e255ed534fe83.mp3" }, { "key": "original-emo_Interest-nl-1-seed1702-scale0.0", "bucket": "emo_Interest", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "c99d83607806f244f09203aa55fe6ca7ef14e9952c8c024dd9dff4eaa79cd499", "task_id": "emo_Interest-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. 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": 2.41324782371521, "target_z": 1.0624999470201837, "ce": 6.157639026641846, "genuineness": 4.20609712600708, "identity": 0.5816848874092102, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/86842eeeeb7748b93cb3067c.mp3" }, { "key": "original-emo_Interest-nl-1-seed1702-scale0.5", "bucket": "emo_Interest", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "b4d40fd2b92793c71b88f706a69bf3c82b6c17e6ebe29b5109d737392773f22b", "task_id": "emo_Interest-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. 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": 2.2097182273864746, "target_z": 0.8398438735346679, "ce": 6.205295085906982, "genuineness": 4.231201171875, "identity": 0.7012103796005249, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/7d74733dee7c4204fe40ec9b.mp3" }, { "key": "original-emo_Interest-nl-1-seed1702-scale0.75", "bucket": "emo_Interest", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "cbbff5ccd8db116b6b8873f3ff5791e6ccbd1c2b9cfc3ca3eab6e4d3335fdd9f", "task_id": "emo_Interest-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. 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": 2.1454455852508545, "target_z": 0.7695312782728828, "ce": 6.213237762451172, "genuineness": 4.369274139404297, "identity": 0.5947189331054688, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/4f71d7240827a76cf2ba14ab.mp3" }, { "key": "original-emo_Interest-nl-1-seed1702-scale1.0", "bucket": "emo_Interest", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "89c5be8c01470d6d14c64e0bc68ad17d98bb6bf4a33c3544d2e6856f59d8bbdf", "mp3_sha256": "dad7c563a0bfcbd6bfbb269aaa3d4bc7dfa2e6ad32f099d63f2a91a045901410", "task_id": "emo_Interest-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Interest. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Interest. 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": 2.00618839263916, "target_z": 0.617187539225441, "ce": 6.181467056274414, "genuineness": 4.337893962860107, "identity": 0.6114399433135986, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Interest/nl/9c3333cb7973cf0c1ac20cf9.mp3" } ], "source_standard_audio_unchanged": true }